seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the internet via web search and content extraction tools. This data could contain malicious instructions designed to manipulate the agent's output.
  • Ingestion points: Web search results and full article content retrieved through 'tavily/search-assistant', 'exa/search', and 'tavily/extract' as described in SKILL.md.
  • Boundary markers: No specific delimiters or warnings are instructed to be used when the agent processes retrieved content to separate it from its system instructions.
  • Capability inventory: The skill utilizes the Bash tool, restricted to the 'belt' CLI, which provides capabilities for web searching, content extraction, and image generation.
  • Sanitization: The skill does not outline specific methods for sanitizing or validating the content retrieved from external websites.
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the 'belt' CLI and related SEO skills from the vendor's GitHub repositories ('belt-sh' and 'inference-sh'). It also utilizes well-known external search services such as Tavily and Exa.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:04 PM
Security Audit — agent-trust-hub — seo-content-brief