ClawAudit verdict
mbti-from-ai
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill analyzes user chat history to infer MBTI personality types, ensuring data privacy and secure processing.
⚠ 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.
95
security
100
transparency
90
maintenance
Findings (2)
Pattern match low
Uses XMLHttpRequest — network access
README.md · prose · downgraded · XMLHttpRequest
Pattern match low
References agent memory files
scripts/extract_messages.py · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Is this flag fair?
Thanks — recorded.