Security audit
Narrative Fallacy
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only reasoning skill that helps users question overly tidy causal stories, with no executable code or hidden access requests.
This skill is safe to install from a security perspective. It will influence how an agent critiques causal stories and business lessons, so users should expect it to make responses more skeptical and probabilistic, but it does not add special permissions or perform actions outside normal text guidance.
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.