Back to skill
Skillv1.0.4
VirusTotal security
Elicitation - how to talk with humans and ask them questions? · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
BenignApr 28, 2026, 3:22 AM
- Hash
- e93b4575b301302b853fc05e17eeedd3c4bcb371dc06404ae70fa4689550943e
- Source
- palm
- Verdict
- benign
- Code Insight
- Type: OpenClaw Skill Name: elicitation Version: 1.0.4 The skill bundle consists entirely of markdown files providing extensive academic documentation and instructions for an AI agent on how to conduct psychological elicitation through natural conversation. The `SKILL.md` file contains instructions for the agent to evaluate its own performance and provide feedback, which is a form of prompt injection, but these instructions are strictly aligned with the stated purpose of the skill and do not instruct the agent to perform any unauthorized actions, exfiltrate data, or bypass security. Furthermore, the `language-inference.md` file explicitly includes 'Ethical Considerations' regarding transparency, humility, consent, and bias awareness, indicating a responsible approach to the techniques described. No evidence of malicious execution, data exfiltration, persistence, or obfuscation was found across any of the files.
- External report
- View on VirusTotal