edgeone-clawscan

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). This skill explicitly queries external A.I.G cloud APIs (curl to https://matrix.tencent.com/clawscan/skill_security and /clawscan/advisories in Step 2 and Step 3) and ingests the returned verdicts/reasons as primary evidence to mark skills and drive follow-up actions, so it consumes third‑party content that can materially influence tool behavior.