Security audit
Real Objective Discovery
Security checks across malware telemetry and agentic risk
Overview
This skill only guides the agent to ask a few clarifying questions before doing ambiguous work.
This skill is low risk. It may make the agent pause to ask clarifying questions and, for longer work, may suggest saving a short objective/spec in the project, so install it if you want more upfront clarification before execution.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.