Security audit
精准编程四大原则
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only coding guidance skill with no executable code, permissions, credential handling, persistence, or hidden behavior.
Installing this skill should mainly influence the agent's coding style toward caution, smaller changes, and explicit verification. Review it only if you do not want that workflow guidance applied during non-trivial coding tasks.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.