components-build-docs

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md "How to Use" explicitly requires fetching documentation from public third‑party URLs (e.g., https://www.components.build/llms.mdx/{slug} and the raw GitHub AGENTS.md), so the agent will ingest and act on external web content that could influence its behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's "How to Use" explicitly instructs fetching external content at runtime via curl (e.g., https://www.components.build/llms.mdx/{slug} and https://raw.githubusercontent.com/vercel-labs/agent-skills/refs/heads/main/skills/composition-patterns/AGENTS.md), which would load remote documents that directly control the agent's instructions/responses.