JWT
Security checks across malware telemetry and agentic risk
Overview
This appears to be a documentation-only JWT security skill with no evidence of code execution, data access, persistence, or hidden behavior.
Reasonable to install if you want JWT security reference material. Because it discusses attacks, use it for authorized defensive review and avoid pasting real live JWTs, private keys, or production secrets into prompts unless you intend the agent to analyze that sensitive data.
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
65/65 vendors flagged this skill as clean.