ia-verification-before-completion
Security checks across malware telemetry and agentic risk
Overview
This skill is an instruction-only verification checklist that tells agents to run relevant local checks before claiming work is complete.
Before installing, expect the agent to run verification commands such as tests, builds, linters, local HTTP checks, or dry-run infrastructure commands before reporting success. Make sure those commands are safe for your environment and do not point at production or print secrets in logs.
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.