Back to skill
Skillv1.0.1
VirusTotal security
NOVA Memory · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 29, 2026, 5:21 AM
- Hash
- 5e34f1fac656656026178bd463322cda026a211255e45ae6d78465511322296e
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: nova-three-level-memory Version: 1.0.1 The skill bundle defines a 'Three-Layer Memory Architecture' that grants the AI agent significant autonomy to self-modify its core identity and behavioral rules based on conversation history. It instructs the agent to perform high-risk operations such as managing systemd services, cron tasks, and executing shell commands (e.g., 'node skills/self-iterator/iterate.js' and 'git commit') for self-maintenance. This architecture is highly susceptible to persistent indirect prompt injection, where malicious user input could be 'distilled' into permanent system constraints or identity changes.
- External report
- View on VirusTotal