Security audit
executing-plans
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent workflow helper for executing written development plans with verification and stop points.
Install this only if you want an agent workflow that follows written implementation plans step by step. Review the plan before execution because the skill is designed to carry out code changes, but the artifact includes clear stop points and verification requirements.
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
57/57 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.