Security audit
ZM 经典表达与写作质量
Security checks across malware telemetry and agentic risk
Overview
This is a writing-quality guidance skill with no executable code, credential use, persistence, or hidden high-impact behavior.
Reasonable to install for writing and editorial-quality review. Treat any drafts you provide as content the agent will process, and keep normal human review for publication decisions, but there is no artifact-backed evidence of malicious or suspicious behavior.
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
60/60 vendors flagged this skill as clean.