Write

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

• Third-party content exposure detected (high risk: 0.90). The skill's research.md explicitly requires sub-agents to perform web searches and record external sources/URLs into research/{piece-id}/sources.md (e.g., "standard" = quick web search, "thorough" = deep research), which the agent is expected to read and use to inform drafting and decisions, exposing it to untrusted public web content that could carry indirect prompt-injection instructions.