Security audit
logic
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only reasoning aid that keeps scoped notes under ~/logic and does not show evidence of hidden execution, credential use, network access, or destructive behavior.
Install if you want an agent to use a more structured reasoning style and keep lightweight local notes under ~/logic. Be aware that heartbeat maintenance may update those local reasoning files, but the artifacts do not request credentials, network access, broad filesystem access, or destructive authority.
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.