planning-with-files

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and examples explicitly instruct the agent to perform web/search/browser operations (e.g., "WebSearch ..." in examples) and to ingest/write those web/search results into findings.md (the Security Boundary and templates state "findings.md ingests untrusted third‑party content"), so the agent will read untrusted, public web content as part of its workflow and that content can materially influence planning/next actions.