Security audit
AgentRank: verify an agent before you pay
Security checks across malware telemetry and agentic risk
Overview
This skill is a read-only reputation lookup guide for checking agent counterparties before payments, with no hidden code or persistence found.
Before installing, understand that this skill relies on an external AgentRank service and may share queried wallet addresses or domains with that service. Treat the score as one input for payment or trust decisions, not as proof of safety or financial advice, and review any MCP tool permissions before adding the server.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.