vs-grill-me

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Pre-scan and Subagents sections explicitly instruct the agent to search external/public repositories and web projects (e.g., "search for how other projects" and use octocode/GitHub search tools), so the agent will fetch and interpret open, user-generated third‑party content that can materially influence its recommendations.