clj-skill-eval
Warn
Audited by Snyk on Sep 15, 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: 0.80). The skill prompt instructs the agent to use the
--dangerously-skip-permissionsflag when executing subagents, which bypasses security constraints and confirmation mechanisms.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata