firecrawl-web

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves and processes untrusted web content, creating a surface for indirect prompt injection where malicious instructions embedded in a webpage could influence the agent's behavior.\n
  • Ingestion points: Markdown content, metadata, and search results fetched from external URLs via the Firecrawl API in fc.py.\n
  • Boundary markers: Absent. The scraped content is printed directly to the agent context without delimiters or explicit instructions to ignore embedded directives.\n
  • Capability inventory: The skill is configured with access to Bash, Read, and Write tools, which increases the potential impact of a successful injection.\n
  • Sanitization: Absent. No filtering, escaping, or validation is performed on the retrieved content before it is passed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 04:32 AM
Security Audit — agent-trust-hub — firecrawl-web