ClawAudit verdict

agent-selfie

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

Generates avatar images via the Gemini API using a user-provided GEMINI_API_KEY; standard API usage for the stated creative image generation purpose with no exfiltration of sensitive data.

⚠ 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.

55
security
90
transparency
80
maintenance

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your_key_here

Pattern match medium

Accesses shell history/config

INSTALL.md · prose · downgraded · ~/.zshrc

Pattern match low

Python urllib.request — network access

scripts/selfie.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

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

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: GEMINI_API_KEY). Requires 1 system binary.

Is this flag fair?

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