Security audit
悟道 · A股行情数据
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent and openly maintainer-focused, but it includes high-impact moderation workflows and a review helper that defaults to running nested Codex with sandbox bypass/full filesystem authority.
Install only in a trusted ClawHub maintainer or Convex development workspace. Before using autoreview, consider setting `AUTOREVIEW_YOLO=0` or passing `--no-yolo`; be aware fallback reviewers may receive generated diffs. Use moderation and publishing workflows only with the intended account, explicit targets, and confirmation for any write action.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.