ClawHub
Back to skill

Security audit

Mustache

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Mustache.js guidance skill; its trigger wording is broad, but it does not include executable code, hidden data access, or persistence.

Safe to install as a Mustache.js reference skill. Be aware it may be selected for broad templating requests, and review npm package provenance before running the install commands. Avoid unescaped/raw HTML output or global escape overrides with untrusted data.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger clause is broad enough to activate on many generic templating or code-generation requests, not just clear Mustache-specific use cases. In an agent environment, over-broad activation can cause the wrong skill to take control, leading to inappropriate guidance, unsafe template rendering patterns being suggested in irrelevant contexts, or interference with more suitable skills.

Static analysis

No suspicious patterns detected.