ralphmode

Warn

Audited by Snyk on Mar 11, 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 (medium risk: 0.60). The prompt explicitly instructs reducing approval friction (including examples with “--dangerously-bypass-approvals-and-sandbox” and “--yolo” flags) and recommends applying user-global configs, which can enable an agent to operate with elevated autonomy and bypass safety checks even though it does not directly ask for sudo, system-file edits, or user creation.

Issues (1)

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 01:20 PM
Issues
1