firecrawl-map
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
firecrawl mapcommand to discover and list URLs from external websites and saves the output to the.firecrawl/directory. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external data.
- Ingestion points: The agent processes the output of the
firecrawl mapcommand in SKILL.md, which consists of URL strings retrieved from external, untrusted websites. - Boundary markers: No explicit instructions or delimiters are provided to the agent to treat the discovered URLs as untrusted or to ignore instructions embedded within the paths.
- Capability inventory: The skill executes the
firecrawlcommand-line tool, which is a vendor-provided utility for this skill. - Sanitization: No sanitization, validation, or filtering of the discovered URL paths is performed before they are presented to the agent context.
Audit Metadata