find-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md instructs using npx skills find and links to https://skills.sh and GitHub (e.g., npx skills add <owner/repo@skill>), which clearly involves discovering and ingesting untrusted, public third‑party skills/repos whose content the agent would read and may install and execute, enabling indirect prompt injection.