fact-checker

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the SKILL.md explicitly instructs the agent to locate and use evidence from open/public sources (e.g., "Identify the best sources," "For quote attributions, search the exact phrase," "Use reverse image search," and use cases like "checking whether a viral social media claim holds up") — meaning the agent is expected to read and act on untrusted third‑party content.