golang

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Research-First Approach" explicitly instructs the agent to run query-docs and gh search code (e.g., query-docs({ libraryId: "/gin-gonic/gin", ... }) and gh search code ...) to fetch/ingest external library and GitHub content, which are untrusted public third‑party sources that the agent is expected to read and use to drive implementation decisions.