firecrawl-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of content from external websites via the FireCrawl API, which introduces a potential surface for indirect prompt injection. \n
  • Ingestion points: Data retrieved from the FireCrawl API as described in the Output section of SKILL.md. \n
  • Boundary markers: The skill does not include specific boundary markers or instructions to the agent to ignore instructions embedded in the retrieved content. \n
  • Capability inventory: The skill allows use of the Write, Edit, and Bash(npm:*) tools, which could be leveraged if an indirect injection is successful. \n
  • Sanitization: No specific data validation or sanitization routines are mentioned for the external data. \n- [COMMAND_EXECUTION]: The skill requests permission to use the Bash tool with npm capabilities (Bash(npm:*)) in its metadata. Although no specific shell commands are provided in the file, this permission allows the agent to install and execute arbitrary Node.js packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 10:58 AM