firecrawl-agent
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include the use of
npx firecrawl-cli, which downloads the vendor's command-line interface from the npm registry at runtime. - [COMMAND_EXECUTION]: The skill uses
firecrawlandfirecrawl-clivia Bash to perform autonomous extraction, job management, and feedback reporting. - [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to navigate and process content from untrusted external websites, creating a surface for indirect prompt injection.
- Ingestion points: External websites accessed through autonomous navigation or user-provided URLs.
- Boundary markers: There are no configured delimiters or instructions to ignore commands found in the scraped content.
- Capability inventory: The skill includes capabilities to write extraction results to the local filesystem and execute shell commands via the Firecrawl CLI.
- Sanitization: No validation or sanitization mechanisms are described for the content retrieved from external sites.
Audit Metadata