File appears to expose a hardcoded API secret or token.
Critical
- Code
- suspicious.exposed_secret_literal
- Location
- SKILL.md:72
Security audit
Agent Skills Tools
Security checks across malware telemetry and agentic risk
Overview
This is a local, user-run security audit helper for checking other skill packages, with no evidence of hidden data export, persistence, or destructive behavior.
Install this if you want a simple local audit script for other skill packages. Run it on specific directories you intend to inspect, treat its findings as heuristic checks rather than proof of safety, and be aware that scan output may include file paths or matching lines from the scanned content.
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
Detected: suspicious.exposed_secret_literal