ADHD Support

• Verdict: Pass
• Analyzed: May 11, 2026, 4:54 AM
• Findings: 0
• Version: 1.0.4
• Hash: e5c07f5359e3a0d37e8c80a02bb928c50fceb46ced4b3d49dc9226fba5db03d4
• Source: palm
• External report: View on VirusTotal

Overview

Type: OpenClaw Skill Name: adhd-support Version: 1.0.4 The OpenClaw skill bundle is classified as benign. While it extensively uses prompt injection techniques within `SKILL.md` and `references/templates.md` to guide the AI agent's behavior and conversational flow (e.g., instructing the agent to switch modes, interrupt users, or prioritize certain actions), these instructions are entirely aligned with its stated purpose of providing cognitive support for ADHD. Crucially, `SKILL.md` explicitly includes a security-positive instruction: 'Never attempt to run timers, shell commands, or system notifications on behalf of the user.' This directly prohibits the agent from performing actions commonly associated with malicious intent, such as arbitrary code execution or system manipulation. There is no evidence of data exfiltration, persistence mechanisms, or any other harmful behavior.