ClawAudit verdict

anvevoice

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

A documentation/setup skill describing AnveVoice's SaaS platform capabilities via MCP tools; no concrete execution sinks or exfiltration are present despite executionSinkDetected=true, and the described functionality (voice AI widgets) matches the stated purpose.

⚠ 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.

68
security
90
transparency
70
maintenance

Findings (2)

Pattern match critical

<script> tag in markdown — potential code injection

README.md · code · <script

Pattern match low

Accesses sensitive environment variables

SKILL.md · prose · downgraded · process.env.ANVEVOICE_API_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class G). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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