Security audit
内容设计写作技巧
Security checks across malware telemetry and agentic risk
Overview
This is a plain writing-guidance skill for structuring persuasive content and does not request system access, credentials, commands, network use, or persistence.
Before installing, consider that this skill is aimed at persuasive content writing, including emotional and social-proof techniques. It appears safe from a system-access perspective, but users should apply it ethically and avoid misleading audiences.
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.