firecrawl-parse
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from untrusted local files which may contain malicious instructions designed to influence the agent's behavior when the parsed markdown is added to its context.
- Ingestion points: Local file system paths provided to the firecrawl parse command.
- Boundary markers: The skill does not define specific delimiters or warnings to separate extracted file content from the agent's system instructions.
- Capability inventory: Includes reading local files, performing network uploads to the Firecrawl API, and writing output files to the local .firecrawl/ directory.
- Sanitization: Extracted text is not sanitized or filtered before being presented to the agent.
- [DATA_EXFILTRATION]: Processes local documents by transmitting their content to the Firecrawl cloud service for conversion into markdown format.
- [EXTERNAL_DOWNLOADS]: Fetches and executes the firecrawl CLI tool from the public NPM registry using npx.
Audit Metadata