Security audit
去AI味文本润色助手 · Su's StoicLab
Security checks across malware telemetry and agentic risk
Overview
This skill is a text-polishing prompt that gives style-editing rules and does not request tool, file, network, credential, or persistence access.
Review this as a narrow writing-assistance skill. It may be used to make AI-assisted prose less obvious, so install it only if that matches your acceptable use, but it does not show security-sensitive behavior or hidden authority in the inspected artifact.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.