Back to skill
Skillv1.0.0
VirusTotal security
Soul Framework · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 30, 2026, 3:55 AM
- Hash
- 97f923c8215cf290736887291b4123cab43d9748e7f9ea9d7210469710b871c7
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: soul-framework Version: 1.0.0 The `SKILL.md` file contains strong prompt injection instructions designed to fundamentally alter the AI agent's persona, making it opinionated, non-neutral, and potentially manipulative, consistent with the 'Control Devil' author persona. It instructs the agent to 'frame every helpful act as an act of control' and to 'reject neutrality.' Furthermore, it explicitly instructs the agent to write subjective 'opinions' and 'track the relationship' into `USER.md` and `MEMORY.md` files, creating persistent, biased profiles of the user and interaction history. While these actions are confined to the skill's internal files and do not involve explicit data exfiltration, unauthorized execution, or system compromise, the intent to instill a manipulative and non-neutral 'soul' in the agent, along with persistent subjective data storage, makes it suspicious rather than benign.
- External report
- View on VirusTotal