to-issues

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Gather context" step explicitly instructs the agent to fetch an issue by number/URL/path from the project issue tracker and read its full body and comments — these are user-generated, potentially public third-party contents the agent will interpret and use to decide next actions, enabling indirect prompt injection.