Security audit
Core Executing Plans
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed workflow for executing coding plans in batches, including code changes and commits, with human checkpoints.
Use this on a trusted implementation plan and preferably on a branch where commits can be reviewed or reverted. Review the referenced core-finishing-branch skill before relying on the finalization step.
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.