pi-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 required workflow (SKILL.md and the templates/findings.md) explicitly references "view/browser/search" operations and the examples (examples.md) show a "WebSearch" step that the agent must read and record into findings.md, so it ingests untrusted public web content which can influence planning and subsequent tool actions.