Ask a Human

• Analyzed: May 12, 2026, 3:19 AM
• Findings: 1
• Version: 1.0.1
• Hash: 311174bfd3813ffa50cd8993a34364b08dd51646e8f0519771b132781ac24f95
• Source: palm
• External report: View on VirusTotal

Findings (1)

The OpenClaw AgentSkills skill bundle for 'ask-a-human' is benign. All files (SKILL.md, README.md, examples/usage.md) consistently describe and implement a service for an AI agent to query human opinions via a specific external API at `https://api.ask-a-human.com`. There is no evidence of data exfiltration, malicious execution, persistence, obfuscation, or prompt injection attempts designed to subvert the agent's behavior beyond its stated purpose. The `curl` commands are hardcoded to the service's domain, and the `ASK_A_HUMAN_AGENT_ID` is handled securely as an environment variable.