skill-vetter

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Read ALL files in the skill" and includes quick-vet curl commands that fetch repo contents and raw files from public GitHub (e.g., api.github.com and raw.githubusercontent.com), so the agent will ingest untrusted, user-generated third-party content that can influence its vetting decisions.