ClawHub

Publish Checklist

Security checks across malware telemetry and agentic risk

Overview

This is a simple pre-publication checklist with broad workflow guidance but no code, credentials, persistence, or data access.

Install this if you want a strict checklist before public-facing work. Be aware it may trigger broadly for PRs, issues, posts, and emails, and it may encourage bilingual PR/Issue text even where your project does not require it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is extremely broad, covering essentially any public release action such as posting, emailing, filing PRs/issues, or publishing skills. In an agent system, this can cause the skill to be auto-invoked in many unrelated contexts, increasing prompt-surface area and making the checklist's behavioral requirements influence outputs unexpectedly.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The instruction to always use bilingual Chinese/English for PRs and Issues imposes an output policy without user opt-in. This can override user intent, leak language preferences into contexts where they are unnecessary, and create unwanted or noncompliant disclosures in automated publishing workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal