看得清 Readable Output · Readability Layout / 多语言排版
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk readability skill that only tells the agent how to reformat long answers more clearly while preserving the original text.
This skill is appropriate if you want clearer summaries of dense AI responses. Because it changes presentation, keep checking the preserved raw wording when exact meaning matters, and review the separately linked plugin or browser companion on its own before installing those components.
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
VirusTotal findings are pending for this skill version.