pierre-guard

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent to verify and grep the upstream public GitHub repo (https://github.com/pierrecomputer/pierre) and to diff/read the package’s .d.ts files in node_modules as part of its verification workflow, meaning the agent will fetch and interpret open/public third‑party code that can materially influence upgrade and integration decisions.