Security audit
Agentizer — The inverse of "humanizer"
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent maintenance and Convex workflow helpers, and I found no artifact-backed malicious or deceptive behavior.
Install only if you want repo-maintenance skills that can guide agents to run local development, GitHub, Convex, moderation, and review commands. Pay particular attention to commands that publish PR comments, change moderation state, install packages, or run the autoreview helper with full-access review mode; use the documented confirmation, dry-run, and opt-out flags when appropriate.
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
VirusTotal findings are pending for this skill version.
Static analysis
No suspicious patterns detected.