firecrawl-scraping

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted external content from the web.
  • Ingestion points: Web content is retrieved via scripts/firecrawl_scrape.py from user-supplied URLs.
  • Boundary markers: No specific delimiters or instructions are used to separate the scraped markdown content from agent instructions in the final output.
  • Capability inventory: The skill allows for local file writing via the --output flag in firecrawl_scrape.py.
  • Sanitization: No sanitization or filtering of the scraped content is performed locally; the skill relies entirely on the Firecrawl API's conversion to markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 04:22 AM