firecrawl-developer-index
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes markdown passages from external sources like GitHub issues, pull requests, and public documentation. This content is provided by third parties and is inherently untrusted, creating an attack surface for indirect prompt injection. \n
- Ingestion points: Data enters the agent's context via markdown results from the
api.firecrawl.dev/v2/search/developerendpoint and web content from thefirecrawl_scrapetool. \n - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the retrieved search results. \n
- Capability inventory: The skill facilitates network-based search and web scraping, allowing it to bring diverse external content into the agent's environment. \n
- Sanitization: There are no mentioned mechanisms for sanitizing, filtering, or escaping the retrieved external content before it is presented to the agent.
Audit Metadata