Security audit
反无限循环守护
Security checks across malware telemetry and agentic risk
Overview
This is a small Chinese-language loop-guard skill that is disclosed, purpose-aligned, and does not request sensitive access.
Safe to install based on the provided artifacts. Use it as a lightweight guardrail and tune thresholds for tasks that legitimately need many retries or long runtimes; do not treat the listed performance metrics as independently verified.
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.