firecrawl-search

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the firecrawl CLI and jq utility for performing searches and processing JSON data. These tools are vendor-specific or standard system utilities used according to their intended purpose.- [PROMPT_INJECTION]: The skill processes untrusted data from the web, creating a potential surface for indirect prompt injection.
  • Ingestion points: External data is ingested from web search results and scraped page content saved to the .firecrawl/ directory (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to isolate scraped content from the agent's instructions.
  • Capability inventory: The skill utilizes shell command execution via the firecrawl and jq tools (SKILL.md).
  • Sanitization: There is no evidence of sanitization or content validation for the data retrieved from external URLs before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 11:49 PM
Security Audit — agent-trust-hub — firecrawl-search