ClawHub
Back to skill

Security audit

Ai Astrochemistry

Security checks across malware telemetry and agentic risk

Overview

This is a plain educational astrochemistry skill with no executable code or sensitive access.

Install if you want Chinese-language astrochemistry reference material. Be aware it may activate for broad molecule, comet, or life-origin questions and may answer in Chinese unless your agent overrides language behavior.

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
90% confidence
Finding
The invocation examples are extremely broad and do not constrain scope, which can cause the orchestration system to activate this skill for loosely related prompts about molecules, chemistry, comets, or life origins. Over-broad activation increases the chance of routing users into a domain-specific skill when they did not ask for it, producing irrelevant or misleading answers and creating prompt-surface for unintended behavior.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The description hard-codes Chinese-language output without indicating that language should follow user preference or locale. This can cause incorrect skill selection or poor user experience for non-Chinese users, and in multi-skill systems it may override user intent or make outputs inaccessible.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.