Api Ninjas

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  1.0.2

Overview

This is a disclosed API Ninjas connector through Membrane, with some stale metadata wording and broad proxy capability users should review before use.

Install only if you trust Membrane and API Ninjas for the data you provide. Approve the global CLI install and browser login intentionally, prefer listed actions over raw proxy calls, and review any proxy path, method, headers, query parameters, and body before sending sensitive information.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: The manifest advertises a narrow skill scope focused on managing Organizations, Users, Goals, and Filters, but the body of the skill exposes a broad API Ninjas integration with unrelated actions and generic proxy access. This mismatch can mislead an agent or reviewer about the true capability surface, increasing the risk of overbroad external access and unintended data handling.

Intent-Code Divergence

Medium

• Confidence: 92% confidence
• Finding: The title and overview present the skill as a general-purpose API platform integration, directly conflicting with the narrower manifest description. Such inconsistency weakens trust boundaries because downstream systems may authorize or invoke the skill based on incomplete or misleading metadata.

Description-Behavior Mismatch

High

• Confidence: 98% confidence
• Finding: The documented 'popular actions' include weather, jokes, sentiment, IP lookup, WHOIS, and other capabilities unrelated to the claimed management purpose. This materially expands the operational scope of the skill beyond what a user, orchestrator, or policy engine would reasonably expect from its manifest.

Description-Behavior Mismatch

High

• Confidence: 99% confidence
• Finding: The proxy request feature allows arbitrary access to API Ninjas endpoints, which defeats the safety value of a narrowly described skill and bypasses action-level scoping. In context, this makes the mismatch more dangerous because a seemingly limited integration actually permits broad external API interaction through a generic request primitive.

VirusTotal

65/65 vendors flagged this skill as clean.