symbol
Warn
Audited by Snyk on Jun 27, 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: 0.90). The skill instructs the agent to apply machine-readable policy tags that can change access controls, trigger enforcement actions, and touch real system boundaries (even if it requires confirmation before live changes), so it pushes the agent toward modifying system state and potentially sensitive configurations.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata