Coinank Openapi Skill

• Outcome: Pass
• Latest audit: May 28, 2026, 11:31 AM
• Version:
  1.0.0

Overview

This skill is a disclosed CoinAnk market-data API helper that uses a CoinAnk API key and network calls to CoinAnk, with no hidden persistence or destructive behavior found.

Install only if you intend to send a CoinAnk API key to CoinAnk’s OpenAPI service. Use a dedicated CoinAnk key where possible, keep it in COINANK_API_KEY, avoid logging commands that include the header, and ensure query parameters are URL-encoded or safely quoted before execution.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The operation explicitly requires an `apikey` header, but its `security` field is set to an empty array, which signals to tooling that no authentication is required. This mismatch can cause client generators, gateways, or reviewers to treat the endpoint as public, leading to accidental unauthenticated access attempts, missing auth enforcement, or leakage of credentials through ad hoc handling.

Intent-Code Divergence

Medium

• Confidence: 97% confidence
• Finding: The top-level OpenAPI document declares `security: []` and has no populated `securitySchemes`, while the endpoints document a required `apikey` header. This contradiction weakens the contract of the API specification and can mislead downstream tooling into omitting authentication, producing insecure integrations or bypass assumptions during deployment.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The spec requires an API key in a request header for calls to an external third-party service, but it does not clearly warn users that their credential will be transmitted off-platform. In an agent-skill context, this can cause unintended secret disclosure or trust-boundary confusion, especially if users assume the skill operates locally or under first-party control.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The API requires an `apikey` header across operations, but the spec declares empty `security` arrays and provides no security scheme, usage constraints, or warnings about when credentialed requests should be sent. In an agent setting, this increases the chance that credentials are attached broadly or invoked without sufficient user awareness, leading to unnecessary secret exposure to a third-party service.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: Multiple endpoints require an `apikey` header for calls to an external service, but the manifest does not document when those authenticated requests should be invoked or how user consent and trigger scope are constrained. In an agent setting, this can lead to overbroad or unintended transmission of a secret to a third party whenever the skill is selected, increasing risk of credential misuse or unnecessary exposure.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The manifest requires an `apikey` header for requests to `https://open-api.coinank.com` but does not provide a clear user-facing disclosure that a credential will be transmitted to an external service. This is dangerous because users or integrators may unknowingly authorize secret-bearing outbound requests, undermining informed consent and making accidental credential exposure more likely.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The spec requires an `apikey` header for requests to an external service but does not clearly warn users that their credential will be transmitted off-platform. In an agent-skill context, this can lead to inadvertent secret disclosure, misuse of paid API access, or unexpected data sharing with a third party, especially because the global `security` section is empty and the key is modeled as a plain header parameter rather than a documented auth scheme.

VirusTotal

66/66 vendors flagged this skill as clean.