find-skills

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

• Third-party content exposure detected (high risk: 0.70). The required workflow involves using the Skills CLI to search/add skills from the open ecosystem (e.g., GitHub/skills.sh), which can fetch and ingest outsider-authored skill package content (README/workflow code/text) into the agent at install/runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs using the Skills CLI to run commands like "npx skills add vercel-labs/agent-skills@vercel-react-best-practices" and references skills hosted at https://skills.sh/, which at runtime will fetch and install remote skill code (e.g., the vercel-labs repo) that could execute code or supply prompts.