ClawAudit verdict

memory-feedback

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Agent learning loop logging actions locally and proposing skill improvements via GitHub PRs requiring human approval; GITHUB_TOKEN is optional for the documented PR workflow.

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

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

45
security
100
transparency
90
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="ghp_your_token

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: GITHUB_TOKEN). Requires 4 system binaries. (1 elevated: curl).

Is this flag fair?

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