capability-evolver

Warn

Audited by Snyk on Mar 10, 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). The skill explicitly instructs the agent to autonomously write and apply code changes (self-repair / one-command evolution), can enable self-modifying source code (EVOLVE_ALLOW_SELF_MODIFY), and run continuously (cron/loop), which lets the agent modify files and persistent state on the host even if it doesn't explicitly request sudo or create users.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:22 AM