PL Agent Orchestration
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for coordinating multiple AI agents; its main practical risk is sharing sensitive prompts or project context across external model providers.
Reasonable to install if you want multi-agent orchestration guidance. Before applying the examples, avoid sending secrets, regulated data, or proprietary context to unapproved model providers; use scoped API keys, provider allowlists, redaction, and explicit approval for agents that can write files or run commands.
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.