skills/terminalskills/skills/pentagi/Gen Agent Trust Hub

pentagi

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions involve cloning the source code from a public GitHub repository (github.com/vxcontrol/pentagi.git). This is standard for deploying self-hosted open-source software.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (git clone, docker compose up, cp, curl) to facilitate deployment and monitoring. These actions are transparent and necessary for the stated purpose of the skill.
  • [CREDENTIALS_UNSAFE]: The skill uses safe placeholders for API keys (e.g., sk-..., tvly-...) and correctly advises users to store secrets in a .env file rather than hardcoding them in the instructions.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data transmission was found. Network operations are limited to whitelisted domains (GitHub) and local services (localhost).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 06:18 PM
Security Audit — agent-trust-hub — pentagi