Security audit
ai-coding-standards
Security checks across malware telemetry and agentic risk
Overview
This is a local coding-standards helper with disclosed file scanning, optional hook setup, and local plan storage, with no evidence of exfiltration or destructive behavior.
Install only if you want a local coding-standards workflow. Review any Git hook script before enabling it, run scans only on project directories you intend to inspect, and avoid putting secrets or sensitive notes into persisted plan files under ~/.ai_plans.
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.