dead-code-detector

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Multi-Perspective Validation" workflow explicitly instructs spawned agents (e.g., the Intent Agent and History Agent) to search issue trackers, code review / merge request context, and external design docs (open/user-generated sources) and to use those findings to classify and act on dead-code results, which means the agent will ingest and act on untrusted third‑party content.