ClawHub
Back to skill

Security audit

Ai Inorganic Chemistry

Security checks across malware telemetry and agentic risk

Overview

This is a static Chinese-language inorganic chemistry study guide with no executable code, network access, persistence, or sensitive data handling.

Safe to install as an educational inorganic chemistry reference. Users who need multilingual behavior or stricter routing may want the publisher to clarify that answers should follow the user’s preferred language and remain limited to chemistry education.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The usage section provides very broad example prompts without defining when the skill should or should not activate. In an agent environment, vague trigger scope can cause over-invocation, unintended routing, and responses outside the intended chemistry domain, which increases the chance of misuse or policy bypass through overly general chemistry-related prompts.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill metadata and content strongly assume Chinese output without indicating that language selection depends on user preference. This can create unsafe or incorrect routing behavior in multilingual systems, where a skill may respond in an unexpected language and bypass usability, review, or downstream moderation expectations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.