Security audit

Cmc Api Market

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a disclosed CoinMarketCap API reference skill, with some broader endpoint coverage and credential-safety gaps but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you want help with CoinMarketCap API workflows. Keep your CMC API key in an environment variable or secret manager, do not paste real keys into chat or code, and be careful when displaying or storing community posts, comments, usernames, avatars, or API plan/quota details.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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

Findings (8)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The file content materially conflicts with the skill metadata: a skill advertised as a market-wide API reference instead documents content, news, posts, and comments endpoints. This scope mismatch can misroute agents or users into accessing unintended data domains, including community and user-generated content, which increases the chance of privacy, policy, or data-handling mistakes.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The skill manifest describes a market-wide API reference, but this file adds utility endpoints for fiat mapping, price conversion, and especially API key information. Scope expansion increases the chance that an agent will expose or rely on capabilities the user did not request, weakening least-privilege boundaries and making prompt-routing or tool-selection mistakes more dangerous.

Context-Inappropriate Capability

Low

Confidence: 89% confidence
Finding: Documenting `/v1/key/info` gives the skill access to API plan, quota, and usage details that are unrelated to answering market-data questions. While not directly exposing the API key, it enables unnecessary introspection into operational metadata, which can leak billing limits or usage patterns and broadens the available attack surface if an agent is induced to call it.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger text is broad enough to match generic market-related requests, which can cause this skill to be invoked outside its narrow CoinMarketCap API reference purpose. Over-broad invocation can misroute user requests, increase unintended tool use, and expose users to irrelevant external-API workflows when they did not specifically ask for CoinMarketCap or market-wide API operations.

Missing User Warnings

Low

Confidence: 76% confidence
Finding: The skill instructs use of an API key header but does not warn against exposing secrets in prompts, logs, screenshots, or checked-in code. In a tool-using agent context, omission of credential-handling guidance can lead users to paste live API keys directly into conversations or command examples, creating avoidable secret leakage risk.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The documentation encourages use of comments and community post data but does not warn that responses contain user-generated content and profile fields such as usernames and avatars. In an agent setting, this can lead to downstream collection, display, or processing of user data without appropriate minimization or moderation controls.

Missing User Warnings

Low

Confidence: 81% confidence
Finding: The examples require an API key header but provide no guidance on protecting secrets. In practice, users may copy these examples into logs, shared snippets, or client-side code, increasing the risk of credential exposure and unauthorized API use.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The examples repeatedly show direct use of `X-CMC_PRO_API_KEY` without any credential-handling guidance, which can normalize pasting secrets into shell history, logs, shared docs, or screenshots. In an agent skill context, this increases the chance users expose API keys when copying examples or asking the agent to execute similar commands.

Static analysis

No suspicious patterns detected.