firecrawl-developer-index
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which creates a surface for potential indirect prompt injection attacks.
- Ingestion points: External data enters the agent context via matched passages from GitHub issues, pull requests, and documentation through the firecrawl_developer_search tool, as well as full web page content via the firecrawl_scrape tool.
- Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the agent to use when processing retrieved passages or scraped content.
- Capability inventory: The skill utilizes network-based search and scraping capabilities; while no direct shell or file-system access is defined within the skill itself, the untrusted data could potentially influence subsequent agent actions if not handled carefully.
- Sanitization: There are no explicit instructions for sanitizing or escaping the retrieved external content before it is processed or presented by the agent.
Audit Metadata