Security audit
Output-Driven Dev
Security checks across malware telemetry and agentic risk
Overview
This is a simple workflow skill that asks agents to define success criteria and verify work before calling it done, with no hidden access or executable behavior found.
This appears safe to install as a workflow aid. Users should still review any verification commands an agent proposes before running them against important files, production systems, or accounts.
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.