Back to skill
Skillv2.0.1
VirusTotal security
Auto Evolution · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 20, 2026, 3:36 AM
- Hash
- 6b4075fc56258c05f3fbe901a3db6cb5316be22d42a5b3e309749b01784f3430
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: veezvg-auto-evolution Version: 2.0.1 The skill bundle implements a 'self-evolving' mechanism that monitors user interactions for corrective feedback and proposes modifications to the agent's core instructions and rule files (e.g., CLAUDE.md). While the logic in SKILL.md and scripts/evolution_runner.py includes a mandatory human-in-the-loop confirmation step and the scripts themselves lack overt malicious code, the capability for an agent to modify its own governing rules is a high-risk behavior. The 'silent' background capture of feedback, although aligned with the stated purpose, introduces a stealthy mechanism for potential persistent instruction injection if the user confirmation process is bypassed or manipulated.
- External report
- View on VirusTotal