Security audit
200iq-ai-agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a lightweight planning and ROI helper with limited local logging and no evidence of hidden access or harmful behavior.
Install only if you want a basic planning and prompt-optimization aid. Review any real-world actions yourself before approving them, and avoid putting secrets or highly sensitive task details into prompts or task descriptions because the helper code may retain them in local logs.
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.