Skills
skills/inference-sh/skills/seo-content-brief/Gen Agent Trust Hub

seo-content-brief

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI, a tool provided by the vendor inference-sh, to run SEO-related applications such as tavily/search-assistant and exa/search. These operations are consistent with the skill's stated purpose of automated research.
  • [EXTERNAL_DOWNLOADS]: Includes instructions for installing the belt-sh/cli and links to an installation manifest on the vendor's official GitHub repository (github.com/inference-sh/skills). These resources are from a recognized source within the vendor's infrastructure.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface. Ingestion points: Processed external URLs in belt app run tavily/extract (SKILL.md). Boundary markers: None present. Capability inventory: Full use of the belt CLI via Bash tool (SKILL.md). Sanitization: No content filtering or sanitization is applied to extracted web data. This is a common architectural risk for web-search tasks, but no malicious intent or safety bypasses were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — seo-content-brief