workflow-feedback-to-closure

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s workflow explicitly ingests outsider-authored free text at runtime (e.g., “user reports / support messages / app-store reviews”, “Sentry issues and alerts”, and “PR review comments and bot findings”) into normalized ticket content ({source, raw, ...}) that the agent would then use in subsequent LLM steps.