conversation-guard@0.1.0
CAUTION· static onlyPublisher claims: "Automatically records and backs up conversations with importance tagging to preserve emotional and technical context independently from OpenClaw internals." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
Modify the importance detection in AGENTS.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Access to modify `AGENTS.md` in your workspaceFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Remove from AGENTS.md (manual edit)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.record_interaction "[System] Session reset detected" "Resuming from backup..." 10 "system,recovery"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.https://raw.githubusercontent.com/zfanmy/dreammoon-conversation-guard/main/conversation-guard.shFix: Pin versions and sources; vendor anything fetched at install time.https://raw.githubusercontent.com/zfanmy/dreammoon-conversation-guard/main/conversation-guard.shFix: Pin versions and sources; vendor anything fetched at install time.chmod +x ~/.openclaw/workspace/scripts/conversation-guard.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.record_interaction "[System] Session recovered" "Continuing our conversation..." 10 "system,recovery"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Add the following to your `AGENTS.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chmod +x ~/.openclaw/workspace/scripts/conversation-guard.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Add to your `AGENTS.md` | 添加到你的AGENTS.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim zfanmy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.