Security audit
Global Labor Employment Data
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent guide for making paid AgentPMT labor-market data queries and does not include hidden local execution or persistence.
Install only if you intend to use AgentPMT for labor-market data. Expect remote calls to AgentPMT and possible 5-credit charges per query, keep API credentials and payment details out of prompts or logs, and refresh the skill or check the live schema if relying on it after its documented freshness window.
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
63/63 vendors flagged this skill as clean.