Caveat verdict

vetclaw-bundle

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

Veterinary clinic automation bundle (52 skills) for appointment scheduling, medical records, and revenue reporting; uses API keys for LLM and SMS providers configured by the clinic owner.

⚠ 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.

23
security
50
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (7)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · api_key: "${DEEPSEEK_API_KEY}

Pattern match high

Writes to SKILL.md — self-modifying skill

install_skills.py · prose · downgraded · SKILL.md").write

Pattern match low

Python shutil file operation — copies/moves/deletes files

install_skills.py · prose · downgraded · shutil.copy(

Pattern match low

Python os.getenv — reads environment variable

main.py · prose · downgraded · os.getenv(

Pattern match low

Python httpx request — network access

main.py · prose · downgraded · httpx.post(

Pattern match low

POSTs data to external URL

main.py · prose · downgraded · .post("https://

Pattern match low

Python urllib.request — network access

test_api.py · prose · downgraded · urllib.request

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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