forge-address-pr-feedback

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches GitHub PR reviewThreads via the GraphQL query in "Step 1: Fetch Unresolved Threads" and instructs the agent to read and act on reviewer comments and surrounding file context (Step 2–3), which are user-generated, untrusted third-party content that can directly drive commits, replies, and other actions.