Security audit

CoinMarketCap MCP

Security checks for vulnerabilities and agentic risk

Overview

This CoinMarketCap skill is legitimate in purpose, but it is too broad about when it sends crypto-related questions to an external authenticated MCP service.

Review this skill before installing if you want strict control over when crypto questions are sent to CoinMarketCap. It is best suited for live market data, news, and analysis, but users should avoid sending sensitive portfolio, wallet, or investment context unless they are comfortable sharing that context with the configured MCP provider.

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

Findings (1)

other

Note

Location: SKILL.md:4
Finding: Excessive Automatic Network Use and Query-Derived Data Disclosure
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill instructs invocation for ANY cryptocurrency-related question, even when the user does not explicitly request external data. This can cause unnecessary tool use, over-collection of user context, and unintended disclosure of user queries to a third-party MCP service, especially for casual discussion, speculative questions, or mixed-topic conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.