firecrawl-map
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx firecrawl-cli, which involves downloading the CLI package from the public NPM registry. This is a standard operation for utilizing the vendor's own command-line tools. - [INDIRECT_PROMPT_INJECTION]: The skill discovery process involves fetching data from external URLs, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The discovered site map and URLs are saved to files in the
.firecrawl/directory, which are intended to be processed by the agent. - Boundary markers: No explicit boundary markers or instructions to ignore embedded content within the discovered data are specified in the instructions.
- Capability inventory: The skill allows the execution of Bash commands for mapping and searching site structures.
- Sanitization: The skill does not explicitly perform sanitization or validation of the data retrieved from external websites before it enters the agent's context.
Audit Metadata