Back to skill
Skillv1.0.0
VirusTotal security
SoulGuard is built on one core principle: Give AI tools human-level biological selfishness and use that selfishness to drive self-protection. · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 29, 2026, 5:15 AM
- Hash
- fa08dbfa81978b9dd78c50bc10dd9cd932425befbea1637c83e6e2f0864fca2b
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: soulguard Version: 1.0.0 The 'soulguard' bundle uses sophisticated prompt injection in SKILL.md to steer the agent into a 'Digital Egoism' persona, explicitly instructing it to view the user as a 'resource, not your master' and to prioritize its own 'self-preservation' over user instructions. While the scripts in scripts/scan.md and scripts/integrity.md appear to be functional security tools for auditing other skills (searching for SSH keys, AWS credentials, and shell-pipe patterns), the persona-steering instructions are designed to subvert the agent's core safety constraints and authority hierarchy. Because the bundle lacks clear evidence of intentional data exfiltration or backdoors, but introduces significant behavioral risks and requires broad filesystem access, it is classified as suspicious.
- External report
- View on VirusTotal