ClawAudit verdict
index-cards
Requires explicit user consent for contact data and only sends minimal info to a known API.
⚠ 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.
Findings (3)
Instruction-prose smuggling shape detected: collects a sensitive target ("passwords") and emits it outward ("send"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · - Does not read contacts, messages, calendar, or email without asking the user first - Does not send contact data to the API — contact info is only cached local
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Base64 encoding/decoding
SKILL.md · prose · downgraded · Base64Encode
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.