Security audit
Secure Linter
Security checks across malware telemetry and agentic risk
Overview
The skill set appears to be a disclosed collection of ClawHub maintainer and Convex workflow guidance, with no evidence of hidden exfiltration, persistence, or destructive behavior.
Review the elevated helper behavior before use: the autoreview helper can run nested review with broad local access by default, and some workflows can affect GitHub PRs, ClawHub moderation state, or Convex deployments. Use the documented confirmation, dry-run, --no-yolo, and fallback-disabling options when working with sensitive repositories or data.
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
67/67 vendors flagged this skill as clean.