Files

• Analyzed: May 12, 2026, 3:51 AM
• Findings: 1
• Version: 1.0.0
• Hash: 0b8a9161e983aaccc8869f76d313d3e7fe5b1722c867afbc8eefe5227a906109
• Source: palm
• External report: View on VirusTotal

Findings (1)

The OpenClaw AgentSkills skill bundle is classified as benign. The `SKILL.md` file, which contains instructions for the AI agent, explicitly defines and enforces robust security measures. These include strict path canonicalization and validation, blocking critical system directories, explicitly refusing to follow symlinks (identifying them as an attack vector), and crucially, stating 'NO shell scripts for undo' to prevent command injection. The skill's stated purpose of file organization is well-aligned with its instructions, which prioritize safety, user confirmation for bulk operations, and transparency, without any indication of malicious intent, data exfiltration, or prompt injection attempts.