Security audit
API credentials hygiene
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a safety-focused guide for auditing API credential handling, with clear instructions to avoid exposing real secrets.
This looks appropriate to install if you want help reviewing credential-handling practices. Because it is about secrets, keep the agent on the documented read-only path unless you explicitly want edits, and never paste real production keys into the chat.
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.