consensus-agent-action-guard
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a disclosed guardrail that evaluates risky agent actions locally and records audit state without signs of exfiltration or hidden behavior.
Reasonable to install if you want local pre-execution governance for agent actions. Before relying on it, review the configured consensus state path and make sure its blocking policy matches your workflow, since a guardrail skill can affect whether actions proceed.
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.