manipulation-detector
Security checks across malware telemetry and agentic risk
Overview
This skill is a local text-analysis helper that reads user-provided text and reports manipulation-pattern matches without network access, persistence, or hidden behavior.
This skill appears safe to install if you want a local helper for reviewing text. Only point it at text or files you intend to analyze, and treat its output as a rough signal because keyword matching can produce false positives.
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.