tiangolo-library-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill discovers and symlinks SKILL.md files embedded in installed third-party libraries (e.g., the FastAPI package skills discovered via agentskills.io and linked into .agents/), and the agent is explicitly described as reading and applying those embedded SKILL.md files—meaning untrusted package-authored content can directly influence agent behavior.