Security audit

Typescript Skills Tool Free

Security checks across malware telemetry and agentic risk

Overview

This TypeScript style-guidance skill is not malicious, but it asks for write and command authority and uses broad auto-activation language that is larger than its stated purpose.

Review before installing. The skill appears to provide ordinary TypeScript style advice and examples, but it should ideally be narrowed to explicit style-review or code-generation requests and should not use write or shell execution unless you clearly ask it to modify files or run local validation commands.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The skill is described as a TypeScript coding-guidelines assistant, but these sections broaden it into generic create/query/export/modify/save operations with configurable input, config, and output parameters. That mismatch can mislead the agent or user about the true operational scope and enable the skill to be invoked for tasks beyond advisory guidance, increasing the chance of unintended file or command actions when combined with declared write/exec capabilities.

Context-Inappropriate Capability

Medium

Confidence: 96% confidence
Finding: Declaring write capability for a skill whose stated purpose is code-style advice violates least privilege. If the skill auto-activates or is steered by ambiguous prompts, write access could let it modify project files or outputs unnecessarily, turning an advisory tool into one with side effects.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: Stating that the tool auto-activates whenever TypeScript is mentioned creates an overly broad trigger that can capture ordinary conversations, not just requests for coding-style guidance. In the presence of exec and write permissions, this increases the chance of unintended tool use and unnecessary side effects from benign prompts.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger scope includes broad activities like code generation, programming assistance, debugging, testing, and deployment, which exceed the skill's stated purpose as a coding-guidelines assistant. This scope creep can cause the skill to activate in unrelated contexts and leverage privileged tools where a style advisor should remain passive.

Vague Triggers

Medium

Confidence: 97% confidence
Finding: Using mere mention of 'TypeScript' as the activation condition is excessively permissive and makes accidental invocation likely. Because the skill also advertises exec and write, an innocuous conversation about TypeScript could escalate into tool-assisted actions that the user did not specifically request.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.