skill-discovery

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs the agent to run a local discovery script and then load and "follow" arbitrary auto-generated skill content, which could contain instructions that modify system files, create users, or invoke sudo — so it enables potentially state-changing and privileged actions even though it doesn't explicitly request them.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:25 AM