firecrawl-parse

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the firecrawl and npx firecrawl commands via Bash to extract text from local file formats including PDF, DOCX, and XLSX.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch the firecrawl package from the official npm registry, which is a well-known service.
  • [PROMPT_INJECTION]: The skill processes untrusted local document content, creating an indirect prompt injection surface as the parsed output is returned to the agent context.
  • Ingestion points: Local file paths (e.g., ./paper.pdf) provided to the firecrawl parse command in SKILL.md.
  • Boundary markers: No explicit delimiters or isolation instructions are defined for the parsed output within the skill logic.
  • Capability inventory: The skill is restricted to Bash execution for the Firecrawl CLI as defined in the allowed-tools frontmatter.
  • Sanitization: Content conversion and sanitization are handled by the external firecrawl utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 11:00 PM
Security Audit — agent-trust-hub — firecrawl-parse