minimal-fix

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

• Third-party content exposure detected (high risk: 0.70). The skill’s REQUIRED workflow is generic (“Exact failure message, reviewer comment, or issue description” and “File(s) implicated”), and at runtime it would ingest free-form text authored by outsiders (e.g., issue/PR/reviewer comments) into the agent’s LLM context via those provided inputs.