ClawAudit verdict
game-sentiment
Describes a multi‑channel sentiment scan with required user confirmations; no hidden exfiltration.
⚠ 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 (1)
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("post"). 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 · For each available channel, following the verified methods in `references/channel-strategy.md`: - **微博**: m.weibo.cn JSON API via Playwright, multiple keyword
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.