ClawHub
Back to skill

Security audit

Implements a JavaScript literal syntax-based protocol for LLM tool calls. Invoke when needing to enable LLM to call local JS functions using template literal syntax.

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill describing a JavaScript template-literal tool-calling pattern, with no executable code or hidden installation behavior.

Use this only with a runtime that treats model output as data until separately validated. Expose a small allowlist of safe tag functions, sandbox execution, validate arguments, and require user approval for functions that read files, use secrets, access the network, mutate data, or run commands.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description says to invoke it whenever enabling LLM tool calls via JavaScript template literal syntax, but it does not define clear preconditions, scope limits, or safety boundaries. In an agent system, overly broad activation criteria can cause the protocol to be applied in unintended contexts, increasing the chance the model emits executable-looking tool invocations or treats untrusted content as actionable tool syntax.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.