Security audit
GitHub Actions Run Gap Audit
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are transparent maintenance and Convex workflow guidance, with higher-impact commands disclosed and bounded by user-directed controls.
Install only if you want ClawHub/Convex maintainer automation. Before using moderation commands, verify the target and reason because they can affect public skills or user accounts. For autoreview, consider using the documented no-yolo option if you do not want nested review to run with full local access.
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.