fix: block side-effecting command wrappers [AI] by pgondhi987 · Pull Request #87292 · openclaw/openclaw

pgondhi987 · 2026-05-27T12:57:04Z

Summary

Treat side-effecting dispatch wrapper forms as policy-blocked instead of transparent when evaluating exec approval allowlists.
Keep plain GNU time usage transparent when it only reports to stderr, while blocking output-file forms before allowlist matching.
Carry the requested analysis platform into command resolution so BSD/macOS wrapper behavior is tested deterministically from Linux.
AI-assisted.

Linked context

No public issue linked in this PR body.

Real behavior proof (required for external PRs)

Behavior addressed: Exec approval allowlists no longer approve an inner command while preserving a side-effecting wrapper for execution.
Real environment tested: Local Linux checkout with Node 24.15.0, repo Vitest wrapper, and direct OpenClaw exec-approval allowlist probes against the patched code.
Exact steps or command run after this patch: node scripts/run-vitest.mjs src/infra/exec-wrapper-resolution.test.ts src/infra/exec-command-resolution.test.ts src/infra/exec-approvals-analysis.test.ts
Exact steps or command run after this patch: node --import tsx --input-type=module with evaluateShellAllowlist probes for script ~/.zshenv git log -1 --format='payload' on darwin, /usr/bin/time -o ~/.bashrc -a -f 'payload' git status on linux, and /usr/bin/time -p git status on linux.
Evidence after fix: Test Files 3 passed (3); Tests 269 passed (269)
Evidence after fix: bsd-script-darwin {"analysisOk":true,"allowlistSatisfied":false,"segmentSatisfiedBy":[null],"policyBlocked":true,"blockedWrapper":"script"}
Evidence after fix: gnu-time-output-linux {"analysisOk":true,"allowlistSatisfied":false,"segmentSatisfiedBy":[null],"policyBlocked":true,"blockedWrapper":"time"}
Evidence after fix: gnu-time-stderr-linux {"analysisOk":true,"allowlistSatisfied":true,"segmentSatisfiedBy":["allowlist"],"policyBlocked":false}
Observed result after fix: BSD/macOS script transcript wrappers and GNU time -o wrappers are policy-blocked before allowlist matching; plain time -p remains allowlist-transparent.
What was not tested: Full suite and cross-OS runtime execution on macOS/FreeBSD were not run locally.
Proof limitations or environment constraints: The BSD/macOS behavior is covered by platform-parameterized OpenClaw allowlist analysis in this Linux worktree rather than by running BSD script on a macOS/FreeBSD host.
Before evidence: The previous behavior reduced wrapper commands to the inner command for allowlist matching while preserving the raw source command for execution.

Tests and validation

Which commands did you run?

git diff --check

pnpm exec oxfmt --write src/infra/dispatch-wrapper-resolution.ts src/infra/exec-approvals-allowlist.ts src/infra/exec-approvals-analysis.ts src/infra/exec-wrapper-trust-plan.ts src/infra/exec-wrapper-resolution.test.ts src/infra/exec-command-resolution.test.ts src/infra/exec-approvals-analysis.test.ts

node scripts/run-vitest.mjs src/infra/exec-wrapper-resolution.test.ts src/infra/exec-command-resolution.test.ts src/infra/exec-approvals-analysis.test.ts

node --import tsx --input-type=module direct evaluateShellAllowlist probes for the blocked script and time -o forms plus allowed time -p.

What regression coverage was added or updated?

Dispatch wrapper trust-plan tests for BSD/macOS script transcript wrappers and GNU time -o / --output wrappers.
Command-resolution tests proving file-writing wrappers stay on the policy boundary.
Allowlist tests proving the reported wrapper classes no longer satisfy an inner git allowlist while plain time -p still does.

What failed before this fix, if known?

The wrapper allowlist behavior could approve the reduced inner command while execution preserved the raw wrapper command.

If no test was added, why not?

Not applicable.

Risk checklist

Did user-visible behavior change? (Yes/No)

Yes.

Did config, environment, or migration behavior change? (Yes/No)

No.

Did security, auth, secrets, network, or tool execution behavior change? (Yes/No)

Yes.

What is the highest-risk area?

Exec approval compatibility for users who intentionally wrapped allowlisted commands with transcript or output-file wrappers.

How is that risk mitigated?

The change is limited to wrapper policy transparency, preserves non-file-output time behavior, and adds focused regression coverage for blocked and still-transparent cases.

Current review state

What is the next action?

Review gates and GitHub CI are pending.

What is still waiting on author, maintainer, CI, or external proof?

Maintainer review and GitHub CI are pending; direct real-behavior proof has been added above.

Which bot or reviewer comments were addressed?

ClawSweeper's real-behavior proof request was addressed by adding direct patched-code allowlist probe output to this PR body.

clawsweeper · 2026-05-27T13:02:08Z

Codex review: needs maintainer review before merge. Reviewed May 27, 2026, 9:15 AM ET / 13:15 UTC.

Summary
The PR changes exec wrapper resolution and allowlist analysis so BSD/macOS script transcript wrappers and GNU time -o/--output wrappers are policy-blocked while plain stderr-only GNU time remains transparent.

PR surface: Source +82, Tests +96. Total +178 across 8 files.

Reproducibility: yes. from source inspection: current main marks script and time transparent and allowlist evaluation only fails once a segment is policyBlocked. I did not execute a current-main repro because this review was read-only, but the PR body also documents before/after direct allowlist probes.

Review metrics: 1 noteworthy metric.

Exec-approval wrapper policy: 2 wrapper families newly blocked. script transcript wrappers and GNU time output-file wrappers can turn formerly allowlisted inner commands into approval misses.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

Wait for the relevant GitHub CI checks to complete.
Have a maintainer explicitly accept the fail-closed compatibility change for wrapped allowlisted commands.

Risk before merge

This intentionally makes some previously allowlisted wrapped commands require approval, so users who rely on script or time -o/--output around allowlisted commands can see a fail-closed behavior change after upgrade.
The PR's proof covers BSD/macOS script through OpenClaw's platform-parameterized analysis from Linux, not a live macOS or FreeBSD runtime run.

Maintainer options:

Land After Compatibility Acceptance (recommended)
Maintainers can accept the stricter fail-closed exec-approval behavior as the security fix once required CI is green.
Request Cross-OS Proof First
Maintainers can ask for macOS or FreeBSD runtime proof if platform-specific script behavior must be verified outside the Linux analysis harness before merge.
Pause If Existing Wrapper Workflows Must Stay Transparent
If preserving allowlisted transcript/output wrappers is a product requirement, pause this PR and design an explicit strict-mode or migration path instead.

Next step before merge
Protected maintainer label plus security-sensitive exec behavior and compatibility impact make this a human maintainer review path, not an automated repair lane.

Security
Cleared: The diff tightens an exec approval security boundary and does not introduce a concrete supply-chain or secret-handling regression; compatibility risk is tracked separately.

Review details

Best possible solution:

Land the narrow fail-closed wrapper policy after maintainer acceptance of the compatibility change and relevant CI completion, keeping the focused regression tests and proof in place.

Do we have a high-confidence way to reproduce the issue?

Yes, from source inspection: current main marks script and time transparent and allowlist evaluation only fails once a segment is policyBlocked. I did not execute a current-main repro because this review was read-only, but the PR body also documents before/after direct allowlist probes.

Is this the best way to solve the issue?

Yes, the patch is a narrow owner-boundary fix: classify side-effecting wrappers as policy-blocked before allowlist matching and pass the requested platform into command resolution. The remaining question is maintainer acceptance of the compatibility impact, not a different implementation path.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against dc5954b0f8cb.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The updated PR body includes copied live output from direct OpenClaw allowlist probes showing both blocked wrapper cases and the still-allowed plain time -p case after the patch.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The updated PR body includes copied live output from direct OpenClaw allowlist probes showing both blocked wrapper cases and the still-allowed plain time -p case after the patch.
remove rating: 🦪 silver shellfish: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove status: 📣 needs proof: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P0: The PR addresses a security-sensitive exec approval allowlist bypass where side-effecting wrappers could run under an inner-command allowlist.
merge-risk: 🚨 compatibility: The stricter wrapper policy can break existing setups that intentionally wrap allowlisted commands with script or time -o/--output.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The updated PR body includes copied live output from direct OpenClaw allowlist probes showing both blocked wrapper cases and the still-allowed plain time -p case after the patch.
proof: sufficient: Contributor real behavior proof is sufficient. The updated PR body includes copied live output from direct OpenClaw allowlist probes showing both blocked wrapper cases and the still-allowed plain time -p case after the patch.

Evidence reviewed

PR surface:

Source +82, Tests +96. Total +178 across 8 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	5	97	15	+82
Tests	3	96	0	+96
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	8	193	15	+178

What I checked:

Current main transparent wrappers: Current main treats script and time as transparent dispatch wrappers, so a resolved inner command can satisfy allowlist matching unless another policy block applies. (src/infra/dispatch-wrapper-resolution.ts:371, dc5954b0f8cb)
Policy-blocked segments deny allowlist: Exec allowlist evaluation already fails a segment when segment.resolution.policyBlocked is true, so the PR's wrapper policy flag directly prevents allowlist satisfaction. (src/infra/exec-approvals-allowlist.ts:606, dc5954b0f8cb)
PR wrapper policy change: The PR adds timeInvocationWritesOutputFile, marks script non-transparent, and makes time transparent only when it does not write an output file. (src/infra/dispatch-wrapper-resolution.ts:238, 117f28f4fd54)
PR platform propagation: The PR carries the requested analysis platform through shell command analysis into command resolution, which is needed for deterministic BSD/macOS wrapper behavior from Linux tests. (src/infra/exec-approvals-analysis.ts:1201, 117f28f4fd54)
Regression coverage: The PR adds focused allowlist tests proving script and GNU time -o no longer satisfy a git allowlist while /usr/bin/time -p git status still does. (src/infra/exec-approvals-analysis.test.ts:627, 117f28f4fd54)
Dependency contract check: GNU time --help documents -o, --output=FILE as writing to FILE instead of stderr, matching the PR's side-effect boundary.

Likely related people:

Georgi Atsev: git blame attributes the current dispatch wrapper resolution and exec wrapper trust-plan code to commit 9e7c2b3, which also appears as the only local history touch for these central files. (role: introduced behavior; confidence: high; commits: 9e7c2b356bac; files: src/infra/dispatch-wrapper-resolution.ts, src/infra/exec-wrapper-trust-plan.ts, src/infra/exec-approvals-allowlist.ts)
Peter Steinberger: Commit 9e7c2b3 lists Peter Steinberger as a co-author on the broad change that introduced the current exec-approval wrapper files in this checkout history. (role: adjacent contributor; confidence: medium; commits: 9e7c2b356bac; files: src/infra/dispatch-wrapper-resolution.ts, src/infra/exec-wrapper-trust-plan.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

clawsweeper · 2026-05-27T13:06:34Z

ClawSweeper PR egg

✨ Hatched: 🌱 uncommon Frosted Clawlet

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

Merged PRs are hatchable.
Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 🌱 uncommon.
Trait: hums during re-review.
Image traits: location proof lagoon; accessory CI status badge; palette moss green and polished brass; mood determined; pose stepping out of a freshly hatched shell; shell brushed metal shell; lighting cool dashboard glow; background smooth stones and checkmarks.
Share on X: post this hatch
Copy: My PR egg hatched a 🌱 uncommon Frosted Clawlet in ClawSweeper.

What is this egg doing here?

Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

pgondhi987 · 2026-05-27T13:08:39Z

Updated the PR body with direct exec-approval allowlist probe output for the blocked wrapper cases and the still-allowed plain time case. @clawsweeper re-review

clawsweeper · 2026-05-27T13:08:42Z

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

* fix: block side-effecting command wrappers * docs: add changelog entry for PR merge

…026.5.27) (#698) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.26` → `2026.5.27` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.27`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026527) [Compare Source](openclaw/openclaw@v2026.5.26...v2026.5.27) ##### Highlights - Safer local/runtime boundaries: OpenClaw now rejects unsafe command wrappers, malformed CLI numeric options, unsafe Node runtime env overrides, no-auth Tailscale exposure, and non-admin device-role pairing approvals before they can affect live runs. ([#87308](openclaw/openclaw#87308), [#87305](openclaw/openclaw#87305), [#87292](openclaw/openclaw#87292), [#87146](openclaw/openclaw#87146)) - Matrix and auto-reply delivery are steadier: mention previews stay inert, final mention replies deliver normally, shared-DM notices are awaited, MXID parsing ignores filenames, and reasoning-prefixed `NO_REPLY` responses stay suppressed. - Provider and agent reliability improved across OpenAI-compatible embeddings, cached token usage, Anthropic/Codex/Claude runtime state, unsupported tool-schema quarantine, heartbeat templates, and session fallback errors. ([#85269](openclaw/openclaw#85269), [#82062](openclaw/openclaw#82062), [#85416](openclaw/openclaw#85416), [#86855](openclaw/openclaw#86855)) - Plugin and package release paths got tighter: Pixverse ships as an external video plugin with region selection, package exclusions and shrinkwrap inventory match the published npm shape, and release/package smoke commands fail bounded instead of hanging. - Gateway hot paths do less rediscovery by reusing current plugin metadata fingerprints, stable plugin index fingerprints, read-only session metadata, active working stores, status fast paths, and auth/env snapshots. ([#86439](openclaw/openclaw#86439)) ##### Changes - Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. ([#85269](openclaw/openclaw#85269)) Thanks [@dutifulbob](https://github.com/dutifulbob). - Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. ([#85072](openclaw/openclaw#85072)) Thanks [@mbelinky](https://github.com/mbelinky). - Pixverse: add video generation provider support, API region selection, and external plugin publishing. - Plugins: expose approval action metadata for plugin-driven approval surfaces. ##### Fixes - Security/CLI/runtime: harden hostname normalization for repeated trailing dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject loose numeric CLI and gateway options, require admin approval for node device-role pairing, and reject no-auth Tailscale exposure. ([#87305](openclaw/openclaw#87305), [#87292](openclaw/openclaw#87292), [#87308](openclaw/openclaw#87308), [#87146](openclaw/openclaw#87146)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Doctor: validate runtime tool schemas for every configured embedded agent while skipping ACP-only profiles, so bad non-default plugin or MCP tools are reported before assistant turns. - Telegram: route `sendMessage` action replies through durable outbound delivery so completed agent responses remain retryable when the gateway send path times out. ([#87261](openclaw/openclaw#87261)) Thanks [@mbelinky](https://github.com/mbelinky). - Matrix/auto-reply: keep draft previews mention-inert, preserve final mention delivery, send mention finals normally, await shared DM notices, ignore filename-embedded MXIDs, and suppress reasoning-prefixed `NO_REPLY` responses. - Agents/providers: add OpenAI-compatible cache retention, forward cached token usage in chat completions, preserve runtime context before active user turns, strip stale Anthropic thinking, load Claude CLI OAuth for Pi auth profiles, avoid false Codex runtime live switches, and quarantine unsupported tool schemas. ([#82062](openclaw/openclaw#82062), [#87167](openclaw/openclaw#87167), [#86855](openclaw/openclaw#86855)) - Gateway/performance: cache plugin metadata fingerprints and stable plugin index fingerprints, borrow read-only session metadata safely, keep the active session working store hot, keep status on a bounded fast path, and preserve model auth profile suffixes. ([#86439](openclaw/openclaw#86439)) - Package/install/release: align npm package exclusions and inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, cap tsdown heap in containers, bound install/release smoke waits, and harden post-publish verification. - Codex/Auth: bound ChatGPT OAuth token exchange and refresh requests, and honor cancellation across Codex and Anthropic OAuth login flows. - QA/E2E/CI: bound Telegram, kitchen-sink, Open WebUI, ClawHub, MCP, Discord, realtime, labeler, and GitHub API waits; fail empty explicit test, live-media, gateway CPU, startup benchmark, plugin gauntlet, and beta-smoke runs instead of false-greening. - Agents/Codex: keep spawned agent bootstrap files rooted in the agent workspace while running task commands, transcripts, and compaction from the requested cwd. ([#87218](openclaw/openclaw#87218)) Thanks [@mbelinky](https://github.com/mbelinky). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/698

* fix: block side-effecting command wrappers * docs: add changelog entry for PR merge

fix: block side-effecting command wrappers

117f28f

openclaw-barnacle Bot added size: M maintainer Maintainer-authored PR labels May 27, 2026

pgondhi987 assigned steipete May 27, 2026

pgondhi987 added 2 commits May 27, 2026 15:26

Merge remote-tracking branch 'origin/main' into fix/fix-696

3cbd4ae

docs: add changelog entry for PR merge

58621eb

pgondhi987 merged commit 8e41c11 into openclaw:main May 27, 2026

github-actions Bot mentioned this pull request May 27, 2026

📡 Upstream Digest — 2026-05-27 18:20 UTC curtismercier/openclaw-mods#958

Open

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 28, 2026

fix: block side-effecting command wrappers [AI] (openclaw#87292)

78333c0

* fix: block side-effecting command wrappers * docs: add changelog entry for PR merge

SYU8384 pushed a commit to SYU8384/openclaw that referenced this pull request Jun 3, 2026

fix: block side-effecting command wrappers [AI] (openclaw#87292)

68bd3e5

* fix: block side-effecting command wrappers * docs: add changelog entry for PR merge

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

fix: block side-effecting command wrappers [AI] (openclaw#87292)

f4eda31

* fix: block side-effecting command wrappers * docs: add changelog entry for PR merge

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: block side-effecting command wrappers [AI]#87292

fix: block side-effecting command wrappers [AI]#87292
pgondhi987 merged 3 commits into
openclaw:mainfrom
pgondhi987:fix/fix-696

pgondhi987 commented May 27, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 27, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 27, 2026 •

edited

Loading

Uh oh!

pgondhi987 commented May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

pgondhi987 commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Linked context

Real behavior proof (required for external PRs)

Tests and validation

Risk checklist

Current review state

Uh oh!

clawsweeper Bot commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Hatch command

Uh oh!

pgondhi987 commented May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

pgondhi987 commented May 27, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading