research

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow instructs the agent to perform targeted web searches and fetch external documentation and filed GitHub issues (see Phase 0 Step 3 and Phase 4's "Fetch current documentation" / "calibrate filed-issue evidence"), which are open/public third‑party sources (including user-generated content) that the agent must read and that can materially change decisions and next actions.