bootstrap-agent-identity

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

• Third-party content exposure detected (high risk: 0.90). This skill's Step 2 "Task artifact scan" explicitly instructs the agent to read GitHub issues or PR state ("GitHub issues or PR state if the project uses them"), which are untrusted, user-generated third‑party sources that the agent must interpret to reconstruct context and decide next actions, creating a clear avenue for indirect prompt injection.