inspo

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

• Third-party content exposure detected (low risk: 0.10). The required workflow searches and downloads screenshots and metadata from a curated archive of production websites (inspomcp.dev), which represents low-risk active community/public registry fetching of external content.

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

• Potentially malicious external URL detected (high risk: 0.70). The script connects to public endpoints https://inspomcp.dev/api/mcp and https://0nme3pk5am3urwa9.public.blob.vercel-storage.com/captures at runtime to fetch API responses and screenshot assets, representing an unverifiable third-party operational dependency under a weak provenance tier.