agent-self-care
Warn
Audited by Snyk on Mar 17, 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 autonomously kills sub-agents and processes and runs cleanup/rotation scripts that modify files and system state (clear artifacts, rotate logs, write retrospectives), which can disrupt the host even though it doesn't request sudo or create users.
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata