Caveat verdict

self-learning

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Agent self-learning skill that analyzes conversation history and updates local config files; all updates stay local with no credential exfiltration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

48
security
70
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (5)

Pattern match critical

Recursive delete from root or home — destructive command

hooks/openclaw/HOOK.md · code · rm -rf ~

Pattern match medium

References agent memory files

SKILL.md · frontmatter · MEMORY.md

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · CLAUDE.md

Pattern match low

Python os.environ.get — reads environment variable

scripts/memory_update.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/memory_update.py · prose · downgraded · shutil.rmtree(

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installagent_memory

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API