firecrawl-map
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
firecrawlandnpx firecrawlcommands to interact with the Firecrawl API for website mapping. These operations are performed within the scope of the tool's intended purpose. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch thefirecrawlpackage from the official NPM registry, which is the standard distribution method for the author's CLI tool. - [PROMPT_INJECTION]: The tool has an indirect prompt injection surface because it ingests untrusted data from the public web (URLs, sitemaps, and site structures).
- Ingestion points: The tool discovers URLs and metadata from external websites provided as input to the
firecrawl mapcommand. - Boundary markers: No specific boundary markers or 'ignore' instructions are defined within the skill documentation to separate the discovered site data from the agent's instructions.
- Capability inventory: The skill possesses the capability to execute shell commands (
firecrawl,npx) and write output to the local file system (e.g.,.firecrawl/urls.json). - Sanitization: The skill documentation does not specify sanitization or validation logic for the content discovered during the mapping process.
Audit Metadata