prompt-refinement

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

• Third-party content exposure detected (high risk: 0.80). The skill's research template (templates/research.md) and the "Multi-Agent Research" / discovery-phase instructions explicitly direct agents to find and synthesize external open sources (e.g., GitHub projects, documentation, blogs), meaning the agent will ingest and act on untrusted public third‑party content that can influence plans/specs.