Skill

• Analyzed: May 14, 2026, 3:18 AM
• Findings: 1
• Version: 1.2.2
• Hash: 6390e8d5b1ce3ac1bb0d875c671372ab79633ca54b8b354403fb997a5f4d4f35
• Source: palm
• External report: View on VirusTotal

Findings (1)

The OpenClaw AgentSkills bundle for 'aegis-security' is classified as benign. The `SKILL.md` and `package.json` files consistently describe a blockchain security API for AI agents, focusing on scanning tokens, simulating transactions, and checking addresses for threats. Crucially, the instructions for the AI agent repeatedly emphasize strong security and privacy practices, including explicit prohibitions against asking for or storing private keys, seed phrases, or mnemonics. It also mandates user confirmation for paid calls and data sharing. All API calls are directed to the stated `aegis402.xyz` domain, aligning with the skill's purpose, and there is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection with harmful intent.