ClawAudit verdict

atypica-user-interview

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

The skill is an AI-persona interview tool that connects to atypica.ai via MCP or curl using a user-supplied API key; all network access is to the documented service for its stated purpose of simulating user research interviews.

⚠ 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.

60
security
80
transparency
70
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="atypica_xxx

Pattern match medium

apt-get install — installs system packages

scripts/mcp-call.sh · prose · downgraded · apt-get install

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