firecrawl-developer-index

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s workflow uses Firecrawl’s developer index endpoints (HTTP GET|POST https://api.firecrawl.dev/v2/search/developer and the corresponding MCP/CLI wrappers) to read matched passages from issue/PR/readme content in the index based on the user’s query, which is outsider-authored text unless constrained to only trusted first-party sources.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime calls to https://api.firecrawl.dev/v2/search/developer to fetch matched passages that are then injected into answers (model context), so remote content can directly influence prompts and responses.