mint

Warn

Audited by Snyk on Feb 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to "Research solutions using WebSearch when needed" (under "What You Do"), which indicates it will fetch and read open/public web content that could influence its decisions and actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly includes and instructs use of sudo commands, editing /etc/ files (GRUB, drivers, encryption headers), running package/driver installation and recovery commands, and calling execution scripts that perform system changes, so it directly guides privileged modifications to the host system.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 11:11 PM