Api Dev Tool Free

• Outcome: Review
• Latest audit: Jul 23, 2026 · 4:00 PM UTC
• Version: 1.0.0

Overview

The skill is not malicious, but it needs review because it requests file-writing and command-execution authority for broad API development tasks without tight scoping or clear user controls.

Install only if you are comfortable with an API-development assistant that may write project files and run local commands. Use it in a project-specific workspace, review generated changes before applying them, and do not provide callback URLs or sensitive API/project data unless you explicitly intend that data to be sent externally.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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

Findings (6)

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The manifest presents the skill as a free/basic API development helper, but the body broadens scope to full lifecycle orchestration, deployment, and generic create/query/modify/delete operations. This mismatch can mislead users and host agents about the real authority of the skill, increasing the chance that it is invoked for higher-risk actions than expected.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The skill declares exec capability even though the stated use case is a personal API development assistant with largely markdown-driven guidance. Granting shell execution materially increases the attack surface because ambiguous prompts could cause command execution, local file access, package installation, or other system changes beyond what users may reasonably expect.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The invocation examples are broad enough to cover building, refactoring, migration planning, and security assessment without defining activation limits or safety constraints. In a markdown skill with write/exec available, vague prompts can be interpreted expansively, leading the agent to take unintended high-impact actions or produce overconfident security outputs.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The capability text uses generic action verbs such as create/query/export and references runtime configuration without clear guards, making the operational boundary unclear. This ambiguity is dangerous because it encourages over-broad tool use and can cause the agent to infer authority for actions not transparently disclosed to the user.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill exposes write and exec capabilities but does not prominently warn users that it may modify files or invoke system commands. That omission increases the risk of unsafe use because users may treat it as a harmless documentation tool while it actually has the ability to change the local environment.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill references callback URLs and external connectivity but provides no privacy or data-handling warning. This is risky because user prompts, API specs, or project data could be transmitted to external endpoints without users fully understanding that data may leave the local environment.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.