Security audit
Dub
Security checks across malware telemetry and agentic risk
Overview
The skills are high-trust developer and ClawHub staff workflows, but their sensitive actions are disclosed, scoped, and gated by user confirmation or existing authentication.
Install only in an environment where the agent is expected to help with ClawHub staff operations or Convex development. Treat moderation, email, migrations, and review-engine use as privileged workflows: confirm targets and command previews carefully, and avoid running autoreview on sensitive private diffs unless sending that code to the selected model provider is acceptable.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.