Security audit
decisive-action
Security checks across malware telemetry and agentic risk
Overview
This skill is a small guidance-only workflow aid that tells an agent when to ask questions versus proceed, with explicit cautions for destructive or high-stakes work.
Install only if you want your agent to ask fewer clarifying questions in routine cases. The main user-impact is behavioral: it may proceed more often on reversible work, while still directing confirmation for high-risk actions.
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.