setup-matt-pocock-skills

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses repo exploration and reads existing root docs like CONTEXT.md, CONTEXT-MAP.md, and docs/adr/* into the agent’s LLM context at runtime, which could include outsider-authored free text (e.g., content written by others in the repo, such as ADRs or wiki/docs).