find-skills

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using "npx skillkit@latest find" and "npx skillkit@latest install owner/repo" and lists community GitHub collections and an online marketplace (e.g., agentskills.com and community repos), which means the skill will fetch and present/install public, user-generated third‑party skill descriptions and code that the agent would read and that could materially change its behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill explicitly instructs running npx to fetch and execute external packages and install GitHub repos at runtime (e.g., npx skillkit@latest and https://github.com/rohitg00/skillkit / owner/repo installs like vercel-labs/agent-skills), which will download and execute remote code and can supply skills/prompts, so it is a runtime dependency that can control agent behavior.