firecrawl-map

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the firecrawl-cli package from the NPM registry. This is an expected operation for installing vendor-provided tooling from a well-known service.
  • [COMMAND_EXECUTION]: The skill executes shell commands using firecrawl and npx firecrawl-cli to perform site discovery and mapping.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sourced from external websites during the mapping process. 1. Ingestion points: External website URLs and their internal link structures provided as input or discovered during mapping in SKILL.md. 2. Boundary markers: The skill does not implement specific delimiters to separate untrusted site data from instructions. 3. Capability inventory: The agent has access to the Bash tool for executing the discovery commands as defined in SKILL.md. 4. Sanitization: No explicit validation or sanitization is performed on the discovered URLs before they are stored in the .firecrawl/ directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 04:28 PM