verify-before-done
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill that helps an agent verify work before claiming completion, with no hidden code or persistence found.
Install this if you want the agent to be stricter about verifying work before saying it is done. Continue to review any proposed test, command, or real external integration call when it could mutate production, account, financial, or other sensitive data.
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.