seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill links to official CLI installation instructions on the vendor's GitHub repository.
  • [COMMAND_EXECUTION]: Employs the 'belt' CLI to execute search, extraction, and image generation tasks. These commands are consistent with the skill's stated SEO research purpose and are performed via vendor-provided tools.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external URLs via search tools, which presents a surface for indirect prompt injection. This is an inherent risk of search-based research tools and is mitigated by the skill's specific focus on content brief generation.
  • Ingestion points: 'tavily/extract' and 'tavily/search-assistant' in SKILL.md.
  • Boundary markers: None specified.
  • Capability inventory: 'belt app run' and 'npx skills add'.
  • Sanitization: No explicit content sanitization is documented for the retrieved data.
  • [CREDENTIALS_UNSAFE]: Includes instructions for 'belt login' to authenticate with the platform. No hardcoded credentials or unsafe storage practices are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 02:47 AM
Security Audit — agent-trust-hub — seo-content-brief