Security audit
Qa Risk Intuition
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only QA risk assessment skill with limited read/search permissions and no signs of hidden execution or data handling.
Installers should expect this skill to help an agent read and search project materials to produce QA risk assessments. It does not appear to execute code or transmit data, but users should still only invoke it on repositories or documents they are comfortable having the agent inspect.
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
62/62 vendors flagged this skill as clean.