seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References installation instructions and additional skill modules from the vendor's official GitHub repository and registry.
  • [COMMAND_EXECUTION]: Employs the Bash tool to execute infsh CLI commands for keyword research, search intent analysis, and data extraction.
  • [DATA_EXFILTRATION]: Performs legitimate network operations to communicate with external search providers like Tavily and Exa to gather SEO data.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting and processing content from third-party websites.
  • Ingestion points: External web content is retrieved using the tavily/extract and tavily/search-assistant tools as described in SKILL.md.
  • Boundary markers: None are specified; there are no instructions for the agent to treat extracted data with caution or use delimiters.
  • Capability inventory: The skill is granted access to the Bash(infsh *) tool, allowing it to execute CLI commands based on its analysis.
  • Sanitization: No evidence of sanitization or filtering for the extracted web content was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 12:06 PM
Security Audit — agent-trust-hub — seo-content-brief