Security audit
Ai Guardian
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed local Ollama governance tool whose sensitive actions are purpose-aligned and described with local audit, policy, and confirmation controls.
Before installing, confirm you want an agent skill that can inspect and manage your local Ollama models, write policy and audit state under ~/.ai-guardian, and optionally store an encrypted Ollama token. Use the guarded prompt route only when you intend prompts to be scanned and logged as metadata, and treat this preview as governance assistance rather than a fully verified security control.
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.