ClawHub
Back to skill

Security audit

ai-high-quality-briefing

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk briefing/writing skill with minor usability and routing concerns, not a security threat.

Install if you want Chinese-language AI/tech/global-expansion briefings. Before relying on it, check whether the skill lets users override language and whether its trigger wording is narrow enough for your workflow.

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
91% confidence
Finding
The skill description is broad enough to match generic research, summarization, and writing tasks well beyond AI/technology/global-expansion briefings. In agent routing systems, this can cause inappropriate auto-invocation, leading the skill to override more suitable skills, pull in unnecessary web research behavior, or produce outputs in an unintended format/domain.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill mandates Chinese output regardless of user preference, which can conflict with user intent, downstream system expectations, or workflows requiring another language. While not a classic security exploit, hard-coded language constraints can cause policy bypass-like behavior in multi-locale environments by returning unusable content or interfering with correct task handling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal