Back to skill

Security audit

Kleinanzeigen helper

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 Codex with sandboxing and approvals disabled.

Review before installing if you will run it on untrusted branches or in sensitive repos. If installed, use `--no-yolo` or `AUTOREVIEW_YOLO=0` for the autoreview helper unless you intentionally want nested Codex to have full filesystem authority, and treat admin/migration commands as production-impacting operations that require careful confirmation.

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.

View on VirusTotal