docs-discovery

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Steps 2–3) explicitly runs WebSearch for "{library} llms.txt" and "official documentation" and then WebFetches and parses the resulting public documentation and llms.txt URLs, which are untrusted third‑party sources that could contain instructions influencing the agent.