Social Trust Manipulation Detector
Security checks across malware telemetry and agentic risk
Overview
This is a transparent, instruction-only skill for analyzing marketplace reputation signals, with no hidden execution or data misuse found.
This skill appears safe to install as an advisory marketplace-analysis aid. Its conclusions could affect reputation or moderation decisions, so verify the underlying evidence before reporting a publisher, discounting a skill's trust score, or taking action based on a MANUFACTURED or SUSPICIOUS verdict.
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
57/57 vendors flagged this skill as clean.