firecrawl-parse

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx firecrawl-cli, which downloads the official Firecrawl command-line interface from the npm registry to process documents.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from untrusted local files (e.g., PDF, HTML) which may contain embedded instructions designed to influence the agent's behavior during tasks like summarization or question-answering. * Ingestion points: Local document paths passed to the firecrawl parse command. * Boundary markers: No explicit delimiters are used in the instructions to separate document content from agent instructions. * Capability inventory: The skill utilizes shell command execution and file system operations. * Sanitization: Document content is not sanitized or filtered before being processed by the AI service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 03:09 AM
Security Audit — agent-trust-hub — firecrawl-parse