ClawAudit verdict

github-issue-reply-assistant

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

The skill generates reply drafts locally and optionally uses network calls for API access, but it does not exfiltrate data or run untrusted code.

⚠ 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.

98
security
80
transparency
70
maintenance

Findings (1)

Pattern match low

Python os.getenv — reads environment variable

scripts/github_issue_reply_assistant.py · prose · downgraded · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

network_in

Is this flag fair?

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