Security audit
thinking-via-negativa
Security checks across malware telemetry and agentic risk
Overview
This skill is a low-risk thinking aid that asks the agent to consider removing unnecessary complexity before adding new features.
This appears safe to install as a reasoning aid. Users should still apply its own guardrails: do not remove safety controls, tests, validation, or hard-to-restore behavior unless there is clear evidence and a rollback plan.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.