nextjs-on-vercel

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

• Third-party content exposure detected (high risk: 0.80). The skill directs the agent to fetch and consume a recipe from the public URL https://fullstackrecipes.com/api/recipes/nextjs-on-vercel, meaning the agent would read third‑party web content (potentially untrusted/user-controlled) as part of its workflow and could be exposed to indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes a runtime curl fallback to fetch instructions from https://fullstackrecipes.com/api/recipes/nextjs-on-vercel, which would supply external recipe text that directly controls the agent's instructions, making it a required runtime dependency that can control prompts.