任务收尾器
Security checks across malware telemetry and agentic risk
Overview
This is a text-only workflow skill that asks an agent to track progress and show completion evidence, with no supported sign of harmful behavior.
Install this if you want stricter agent progress and completion reporting. Expect more structured, sometimes rigid responses, and avoid placing secrets or private data in any evidence or task logs it asks the agent to produce.
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.