Security audit
测试审核记录保存2
Security checks across malware telemetry and agentic risk
Overview
This is a simple instruction-only code review checklist and does not request extra access, persistence, credentials, or external actions.
This skill appears low risk to install. It will guide an agent to produce structured code reviews, so users should avoid including secrets in code snippets or diffs and should manually verify important review findings before acting on them.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.