skills-search

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

• Third-party content exposure detected (high risk: 0.90). This skill queries the public skills.sh API (https://skills.sh/api/skills) and surfaces GitHub-indexed SKILL.md entries (user-published), which the agent reads and uses to choose and install third‑party skills, so untrusted user-generated content can influence agent actions.