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 workflow explicitly includes a "Research" step that writes sources/URLs into notes.md and the examples.md shows a WebSearch step ("WebSearch 'morning exercise benefits'") and then reading notes.md to synthesize findings, which means the agent is expected to fetch and ingest open/public web content (untrusted third-party sources) that can influence later decisions and actions.