claude-skill

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: 0.75). The skill explicitly enables autonomous, non-interactive file edits (defaulting to --permission-mode acceptEdits) and provides a "bypassPermissions" mode that skips all prompts and allows unrestricted tool use (including Bash), which can lead to running shell commands or modifying system files without approval and thus can compromise the host state.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:30 AM