similar-code

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow in SKILL.md instructs the agent to run searches like code_search/search across “all repos” and “related discussions,” which at runtime can surface outsider-authored free-form text (e.g., issue/RFC/design-doc comments) into the agent’s LLM context for vetting and summarization.