claude-code-mastery

Warn

Audited by Snyk on Mar 22, 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 explicitly enables write-capable agents, automatic hook execution (running arbitrary shell commands without approval), an "Yolo" allow-all permission mode, and a server-filesystem for access beyond the project—configurations that can enable an agent to modify files or execute destructive commands on the host if misused—so it meaningfully increases risk of compromising machine state even though it doesn't directly instruct sudo or user-creation.

Issues (1)

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 01:51 PM
Issues
1