Security audit
verdictswarm
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed token-risk checker that calls VerdictSwarm before trading and does not execute trades itself.
Before installing, understand that token details will be sent to VerdictSwarm's API and that any returned API key should be treated as a secret. The skill can inform trading decisions but does not prove a token is safe or profitable, and any paid x402 request should require explicit approval.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.