security-skills-guide

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to "use WebFetch to retrieve the full README.md" from a public raw GitHub URL (https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md), which is untrusted, user-generated third‑party content the agent would read and could act on.