Security audit

Javascript Toolkit Free

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a JavaScript advice skill, but it asks for shell execution and includes vague file-operation language broader than its stated purpose.

Review before installing. Use it only for explicit JavaScript code advice or snippet validation, and do not let it perform file writes, imports, exports, network diagnostics, or shell commands unless you specifically asked for that action and reviewed the target.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill is presented as a JavaScript pitfalls reference, but these sections authorize generic create/query/export/modify/reset/import/save/convert actions that are not scoped to the stated educational purpose. That mismatch can cause an agent to treat the skill as permission to perform broader file or data operations than a user would reasonably expect, increasing the chance of unsafe side effects or prompt-driven abuse.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The markdown authorizes export/save/modify/import style operations without telling users what data may be affected, where files may be written, or when confirmation is required. In an agent setting, that omission can translate into silent state changes, overwrites, or movement of user data under the guise of a help-oriented skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger conditions are so broad that the skill may activate for common development, debugging, or deployment requests well outside its advertised niche of JavaScript pitfall prevention. Overbroad auto-invocation increases the likelihood that the agent applies this skill in inappropriate contexts, including ones where its exec-oriented guidance or file-operation language becomes risky.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill requests exec-capable operation and suggests command-oriented/network-diagnostic behavior such as running ping, despite being a documentation-style JavaScript best-practices guide. This expands the agent's operational footprint beyond its declared role and could be leveraged to trigger unnecessary command execution or environmental probing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The visible skill description is written in Chinese and the document consistently presents user-facing instructions in Chinese, with no indication that users may choose another language. This can be a language/locale policy concern when the skill is intended for general use across agents and platforms.
Content: No source excerpt is available for this finding.