firecrawl-parse

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash(firecrawl *) and Bash(npx firecrawl *) to execute document parsing commands on the local system.
  • [EXTERNAL_DOWNLOADS]: Downloads and runs the firecrawl CLI from the npm registry via the npx command.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external documents (PDF, DOCX, HTML, etc.), which creates a surface for indirect prompt injection if the files contain instructions designed to manipulate the agent's behavior during summarization or Q&A tasks.
  • Ingestion points: Local files at paths like ./paper.pdf processed by the firecrawl parse command.
  • Boundary markers: No delimiters or protective markers are defined to separate ingested file content from the agent's instructions.
  • Capability inventory: Shell access via Bash for executing Firecrawl CLI tools.
  • Sanitization: No sanitization of document content is described before the output is used for downstream agent tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 06:45 AM
Security Audit — agent-trust-hub — firecrawl-parse