docs: add prompt-guard security skill recommendation#4278
Closed
seojoonkim wants to merge 1 commit intoopenclaw:mainfrom
Closed
docs: add prompt-guard security skill recommendation#4278seojoonkim wants to merge 1 commit intoopenclaw:mainfrom
seojoonkim wants to merge 1 commit intoopenclaw:mainfrom
Conversation
Add recommendation for prompt-guard security skill in the Security defaults section. Prompt Guard provides multi-language prompt injection defense for group chats and multi-user environments. - Detects attacks in EN/KO/JA/ZH - Blocks secret exfiltration attempts - Restricts dangerous commands to owner - Available on ClawdHub
Contributor
|
Better way might be using ACIP instead: It's very comprehensive with a one liner install: |
Comment on lines
+117
to
+119
| ### Recommended: Prompt Injection Defense | ||
|
|
||
| For group chats and multi-user environments, consider adding **[Prompt Guard](https://github.com/seojoonkim/prompt-guard)** — a security skill that detects and blocks prompt injection attacks in 4 languages (EN/KO/JA/ZH): |
Contributor
There was a problem hiding this comment.
[P2] README "Security defaults" section recommends a third-party skill without any safety/trust caveat.
This adds installation instructions for an external “security skill” from an individual GitHub repo. Given this is a security-focused recommendation, readers may assume it’s vetted/official. Consider adding a brief note that it’s a community/third-party skill (not maintained by Moltbot) and that users should review/audit it before installing and granting it access to messages/tools; otherwise it can create a false sense of security or introduce its own risk.
Prompt To Fix With AI
This is a comment left during a code review.
Path: README.md
Line: 117:119
Comment:
[P2] README "Security defaults" section recommends a third-party skill without any safety/trust caveat.
This adds installation instructions for an external “security skill” from an individual GitHub repo. Given this is a security-focused recommendation, readers may assume it’s vetted/official. Consider adding a brief note that it’s a community/third-party skill (not maintained by Moltbot) and that users should review/audit it before installing and granting it access to messages/tools; otherwise it can create a false sense of security or introduce its own risk.
How can I resolve this? If you propose a fix, please make it concise.
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
3 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
Adds a recommendation for the prompt-guard security skill in the Security defaults section of the README.
Why?
Moltbot users running agents in group chats or multi-user environments are vulnerable to prompt injection attacks. Prompt Guard provides:
Changes
Related
Greptile Overview
Greptile Summary
This PR updates
README.md’s “Security defaults (DM access)” section by adding a new “Recommended: Prompt Injection Defense” subsection that suggests installing the third-party Prompt Guard skill viaclawdhub install prompt-guard, and links to the skill’s GitHub repo and ClawdHub listing. The change fits as an additional hardening recommendation for users operating Moltbot in group chats/multi-user environments, complementing the existing DM pairing/allowlist guidance.Confidence Score: 4/5
(2/5) Greptile learns from your feedback when you react with thumbs up/down!
Context used:
dashboard- CLAUDE.md (source)dashboard- AGENTS.md (source)