to-issues

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "busque no issue tracker e leia o corpo completo e comments" (SKILL.md, "1. Junte contexto"), which requires fetching and interpreting user-generated issue tracker content that can influence how issues are drafted and published, so untrusted third-party text could inject instructions into the agent's workflow.