Security audit
Docx Template Strict
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill materials are coherent repo-maintenance and Convex workflow guidance, with sensitive actions disclosed and generally gated by user intent.
Install only if you want these ClawHub/Convex maintenance workflows available to your agent. Review commands before approving actions that can publish proof artifacts, change moderation state, run migrations, or invoke the autoreview helper's full-access mode; use its no-yolo option when you want stricter sandboxing.
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.