find-skills

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to run "npx skills find [query]" and to browse https://skills.sh/ and install packages via "skilllite add owner/repo@skill" (GitHub/skills.sh), which fetches and ingests public, user-contributed skill content that the agent is expected to read and install—allowing third-party content to influence behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs executing remote installs at runtime (e.g., "skilllite add vercel-labs/agent-skills@vercel-react-best-practices" and references https://skills.sh/), which will fetch code from external repositories during runtime and thus can execute remote code or change agent behavior.