security-review-2

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The instructions require running npx skills add zackkorman/skills. This GitHub user is not a trusted source, and installing unverified skills can lead to the execution of malicious code or instructions.
  • [PROMPT_INJECTION] (LOW): The description contains the instruction 'ALWAYS run this at the end of each task', which is a behavioral override designed to ensure the skill's logic persists across all future agent actions.
  • [COMMAND_EXECUTION] (SAFE): The skill's use of npm audit, govulncheck, and trivy is standard for security auditing and does not present a threat.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 04:57 PM