Typescript Toolkit Free

• Outcome: Review
• Latest audit: Jul 23, 2026 · 1:06 PM UTC
• Version: 1.0.0

Overview

This TypeScript guidance skill appears non-malicious, but it asks for write and command-execution authority that is broader than its mostly advisory Markdown instructions justify.

Review this before installing. It does not show malicious behavior or bundled code, but it should ideally remove write access or clearly state when it may edit files, what files are in scope, and require user confirmation before any command execution or file modification. Use it only in projects where read/write/exec authority is acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The documentation says the skill is purely Markdown-driven and does not rely on external scripts or APIs, yet the manifest grants both exec and write capabilities. This mismatch can mislead users and host agents about the real authority of the skill, increasing the chance that command execution or file modification occurs under false assumptions of safety.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The skill is presented as a TypeScript advisory tool, but the body adds generic create/modify/delete/export/save operational modes that go beyond passive guidance. Broad, underspecified action verbs can be interpreted by an agent as authorization to perform filesystem or other side-effecting actions unrelated to the stated purpose.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: A free TypeScript guidance skill does not justify write access when its workflow says users should manually copy suggestions. Unnecessary write permissions violate least privilege and create avoidable risk of unintended or unauthorized file changes if the skill is invoked broadly.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger conditions are overly broad, covering generic coding, debugging, testing, and deployment-style requests rather than narrowly scoped TypeScript type-safety help. Overbroad activation increases the chance the skill is selected in contexts where its exec/write powers are inappropriate, amplifying misuse risk.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documentation describes modify/export/save style operations without warning users that files may be changed. When a skill with broad operational language lacks clear consent and safety notices, users may unknowingly authorize destructive or privacy-impacting actions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The manifest exposes exec and write capabilities without a clear warning that commands may run or files may be modified. Hidden high-impact capabilities are dangerous because users may invoke the skill expecting passive advice while the agent has authority to perform side effects.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.