setup-matt-pocock-skills

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow reads existing repo files (e.g., CONTEXT.md, docs/adr/*, AGENTS.md/CLAUDE.md, and potentially issue tracker content) that may include outsider-authored free text from other contributors; this text is then ingested into the agent’s LLM context during “Explore” and “Confirm and edit”.