vercel-react-best-practices

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read public, user-maintained files from raw.githubusercontent.com (e.g., https://raw.githubusercontent.com/vercel-labs/agent-skills/main/skills/react-best-practices/AGENTS.md and per-rule files), which are untrusted third‑party content the agent is expected to interpret and use to drive coding/refactoring decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to fetch external guidance from https://raw.githubusercontent.com/vercel-labs/agent-skills/main/skills/react-best-practices/AGENTS.md (and per-rule URLs like https://raw.githubusercontent.com/vercel-labs/agent-skills/main/skills/react-best-practices/rules/{rule-name}.md), which would load remote markdown that directly controls prompts/instructions used for refactoring, making it a required runtime dependency that can control the agent.