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 workflow (SKILL.md) instructs using npx skills find and links to https://skills.sh/ and owner/repo@skill-name installs (via the provided install script), which fetches and ingests third‑party skill metadata and code from public sites/GitHub—untrusted content that can materially change agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx to fetch and install external skills at runtime (e.g., the skills.sh link https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices and the repo spec vercel-labs/agent-skills@vercel-react-best-practices), which will download and install remote code/packages that extend agent behavior and can contain prompts or executable install scripts, so this is a runtime dependency that can control prompts or execute code.