Security audit
Google Slides
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent for ClawHub and Convex maintenance, but one review helper defaults to running a nested AI reviewer with full sandbox-bypass authority.
Install only if you trust these ClawHub-maintenance workflows and are comfortable with authenticated moderation commands and the autoreview helper. Prefer running autoreview with `--no-yolo` or `AUTOREVIEW_YOLO=0`, and review any command that can post to GitHub, change ClawHub moderation state, or send diffs to external reviewer CLIs.
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.