Security audit
Claim-to-Source Auditor
Security checks across malware telemetry and agentic risk
Overview
This is a transparent fact-checking skill that reads article evidence and sources to produce audit reports, without hidden installation or execution behavior.
Install only if you want an agent to audit factual claims against local and online sources. When using it, point it at specific articles and evidence locations, and be mindful that generated CSV audit records may contain claims, source notes, and excerpts from sensitive internal materials.
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
50/50 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.