planning-with-files

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow (SKILL.md and templates/findings.md) and examples (examples.md) explicitly require performing "view/browser/search" or "WebSearch" operations and writing those web/browser results (untrusted public URLs/results) into findings.md for later reading and decision-making, so third‑party content from the open web is ingested and can materially affect agent actions.