Security audit
consensus-guard-core
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent local consensus-policy library with expected local state writes and no evidence of hidden network, credential, or destructive behavior.
Use this as shared policy infrastructure rather than an end-user automation skill. For production, install from a trusted package source, use the lockfile or exact dependency pins, audit transitive dependencies, set CONSENSUS_STATE_ROOT to a dedicated non-privileged directory, and allow only trusted workflows to call writeArtifact or writeDecision because those records may influence later decisions.
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.
Static analysis
No suspicious patterns detected.