Security audit
Phy Jwt Auth Audit
Security checks across malware telemetry and agentic risk
Overview
This skill locally audits JWT/OAuth security and may read sensitive tokens or .env files when directed, with no evidence of hidden upload, persistence, or destructive behavior.
Use this skill only when you are comfortable letting the agent inspect JWTs, OAuth scopes, source files, and possibly .env secrets. Prefer expired or test tokens, scope scans to the smallest relevant directory, and redact or rotate any live credentials that appear in the output.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.