fix(skills): honor policy table for dangerous verdicts#1330
Merged
Conversation
Salvaged from PR #1007 by stablegenius49. - let INSTALL_POLICY decide dangerous verdict handling for builtin skills - allow --force to override blocked dangerous decisions for trusted and community sources - accept --yes / -y as aliases for --force in /skills install - update regression tests to match the intended policy precedence
Keep the argparse CLI aligned with the slash command so --yes and -y behave the same as --force for hermes skills install. Add a parser-level regression test.
19 tasks
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…048e6599 Merging the policy-precedence fix salvaged from NousResearch#1007 onto current main, plus the CLI --yes/-y alias consistency follow-up.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…048e6599 Merging the policy-precedence fix salvaged from NousResearch#1007 onto current main, plus the CLI --yes/-y alias consistency follow-up.
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…048e6599 Merging the policy-precedence fix salvaged from NousResearch#1007 onto current main, plus the CLI --yes/-y alias consistency follow-up.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…048e6599 Merging the policy-precedence fix salvaged from NousResearch#1007 onto current main, plus the CLI --yes/-y alias consistency follow-up.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
mainINSTALL_POLICYcontrol dangerous verdict handling intools/skills_guard.py, so officialbuiltinskills actually honor their policy row--forceto override blocked dangerous verdicts fortrustedandcommunitysources--yes/-yas aliases for--forcein/skills installhermes skills installnow accepts--yes/-ytoo, with a parser-level regression testWhy
Current
mainalready resolvesofficial/...sources tobuiltin, butshould_allow_install()still hard-blocks everydangerousverdict before consultingINSTALL_POLICY. That makes the builtin dangerous-policy row dead code and blocks official optional skills likeofficial/email/agentmail.This salvage preserves the contributor's policy-precedence fix and adds a small CLI follow-up so the slash command and argparse CLI behave consistently.
Test plan
python -m pytest tests/tools/test_skills_guard.py tests/tools/test_force_dangerous_override.py tests/hermes_cli/test_skills_hub.py tests/hermes_cli/test_skills_install_flags.py -n0 -qpython -m pytest tests/ -n0 -qFixes #1006