Security audit
AgentTrust — Security Scanner for AI Skills
Security checks across malware telemetry and agentic risk
Overview
AgentTrust is a disclosed security-scanning skill that sends user-selected scan inputs to its external service and gates paid actions on explicit approval.
Install only if you are comfortable sending selected skill content, MCP manifests, endpoint URLs, wallet addresses, or hashes to agenttrust.uk. Use free endpoints by default, and approve paid x402/USDC actions only after checking the exact price and input being submitted.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.