planning-with-files

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to perform external research and ingest public web/GitHub content into its workflow (e.g., "Read Fabric Admin API documentation" in the task_plan.md example and "Search for solutions (use github-repo-explore skill)" in the 3-Strike Error Protocol), and those findings are written to and used from findings.md to influence decisions and next actions.