firecrawl-developer-index
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as public documentation, GitHub issues, and pull requests via the
firecrawl_scrapeandfirecrawl_searchtools, which introduces a potential attack surface for instructions embedded in external content. - Ingestion points: External content retrieved from repository evidence, API contracts, and documentation sites via scraping and search tools in
SKILL.md. - Boundary markers: The skill instructions mention citing sources and distinguishing official documentation from issues, but do not provide specific delimiters or instructions to ignore malicious embedded commands.
- Capability inventory: The skill utilizes tools for searching and scraping external web content.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external URLs.
Audit Metadata