typescript-dev
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent, but its autoreview helper defaults to running a nested Codex review with sandbox and approval bypass, which is broader authority than a review gate normally needs.
Install only if you are comfortable with the ClawHub-specific workflows and the autoreview helper's default full-access nested Codex mode. For safer use, run autoreview with --no-yolo or set AUTOREVIEW_YOLO=0, and keep moderation, proof publishing, Convex deploys, and migrations limited to explicit user-approved targets.
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.