vendor-ai-review

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly requires the agent to consume and analyze third-party vendor contract text via the command snippet ("[paste the vendor AI terms]" for /ai-governance-legal:vendor‑ai‑review), so untrusted external content is read and used to drive decisions and negotiation outputs.