kh-assistant

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches project metadata and release information from the official GitHub repository using the gh command-line tool. It also provides commands for users to install related skills from the same vendor organization using npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including GitHub issues and discussions. This is an inherent risk factor where untrusted content could potentially influence the agent's behavior.
  • Ingestion points: GitHub issue content, discussion titles, and documentation files (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Execution of gh, terraform, grep, and npx commands.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 08:49 AM
Security Audit — agent-trust-hub — kh-assistant