principle-never-block-on-the-human
Warn
Audited by Snyk on Aug 9, 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). This skill explicitly instructs agents to "proceed, then present" and to self-heal without blocking the human, which encourages making system changes autonomously and could lead to privileged or state-changing actions without proper confirmation.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata