firecrawl-map
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data access commands were identified. The skill is well-documented and its behavior aligns with its stated purpose of site mapping.
- [EXTERNAL_DOWNLOADS]: The skill references the use of
npx firecrawl-cli, which downloads and executes the Firecrawl utility from the official NPM registry. This is a standard deployment method for the vendor's command-line tools. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to map external websites, it possesses an inherent attack surface for indirect prompt injection via the content it processes.
- Ingestion points: External website content and sitemaps are processed to identify URLs.
- Boundary markers: No explicit instructions are provided to the agent to ignore instructions embedded in the discovered data.
- Capability inventory: Access to the
Bashtool to run mapping and search commands. - Sanitization: The skill relies on the Firecrawl CLI tool itself to handle the sanitization of data retrieved from the web.
Audit Metadata