Security audit

CoinMarketCap Market Overview APIs

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only CoinMarketCap API reference skill with some broad documentation and missing safety cautions, but no hidden execution, persistence, or destructive behavior.

Install only if you want CoinMarketCap API reference material available to your agent. Use your own CMC API key carefully, prefer environment variables over pasted secrets, and treat community posts/comments/news and API usage responses as sensitive or untrusted data when sharing logs or building downstream workflows.

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

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 (27)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill manifest says this skill is for CoinMarketCap market-wide endpoints such as global metrics, fear/greed, dominance data, and charts, but the file documents content, news, posts, and comments APIs instead. This scope mismatch can cause an agent to invoke or recommend unrelated capabilities, including retrieval of user-generated content and profile data, undermining least-privilege assumptions and making downstream misuse more likely.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The trigger text is broad enough that the skill may activate for generic market or chart-related requests even when the user did not specifically intend to use this CoinMarketCap reference. Over-broad activation can cause inappropriate tool use, unnecessary exposure of API-oriented instructions, and increase the chance that users are steered into supplying credentials or using external services unintentionally.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs users to provide an API key in request headers but does not warn against pasting secrets into chat, logs, or shared terminal history. In a skill that explicitly discusses authentication and curl usage, omission of credential-handling guidance materially increases the risk of accidental secret disclosure through prompts, transcripts, screenshots, or shell history.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest says this skill is the API reference for CoinMarketCap market-wide endpoints such as global metrics, fear/greed, indices, trending topics, and charts. This file instead documents community-platform endpoints for trending tokens and community discussions, which is a different API area focused on social/community activity rather than market-wide metrics.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Documenting community posts, comments, and news aggregation in a skill advertised for market metrics expands the effective capability surface beyond the declared purpose. In agent settings, that can mislead tool selection and enable unnecessary access to user-generated content, creating privacy, compliance, and data-handling risks not expected from a market-metrics skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The document presents sentiment-based trading and risk-management guidance as actionable use cases without a clear disclaimer that the content is informational only and not financial advice. In a skill specifically triggered for market sentiment and API usage, this can encourage users or downstream agents to treat the index as a trading signal, increasing the risk of harmful financial decisions.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill manifest says this skill is the API reference for CoinMarketCap market-wide endpoints such as global metrics, fear/greed, indices, trending topics, and charts. This file instead documents utility endpoints for fiat mapping, API key information, and price conversion, which are outside that stated market-wide scope.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The documented /v1/key/info endpoint exposes API plan, credit usage, and rate-limit details about the caller's account rather than market data. That capability does not match a skill described as a complete reference for market-wide CoinMarketCap data like sentiment, dominance, and charts.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest frames the skill around market-wide data endpoints, but this section documents a generic currency conversion tool for crypto/fiat conversion in any direction. Conversion utilities are materially different from global metrics, fear/greed, trending topics, and charts.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest describes this skill as an API reference for CoinMarketCap market-wide endpoints such as global metrics, fear/greed, indices, trending topics, and charts. This file additionally documents latest crypto news, price conversion tools, API key usage inspection, and fiat currency ID lookup, which are separate capabilities not implied by the stated market-wide scope.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest focuses on market API questions like fear/greed, global metrics, BTC dominance, charts, and market sentiment. Documenting GET /v1/content/latest for crypto news introduces a content/news retrieval capability that does not match the declared market-wide reference scope.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: A price conversion tool is a utility endpoint for converting crypto and fiat amounts, not a market-wide metrics, sentiment, index, trending-topic, or chart endpoint as described in the manifest. This creates a semantic mismatch between the skill's stated purpose and the documented capability.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest claims a market-wide API reference centered on market data and sentiment. GET /v1/key/info is an account or credential-usage management endpoint, which is materially different from the skill's stated market-data purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The parameter documentation explicitly states 'Default: en' for language filtering, which imposes a specific language/locale by default. Under SQP-3, forced language behavior can be a policy issue when no user choice or justification is provided.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The comments endpoint exposes user-generated text and profile fields such as usernames and avatars, but the documentation does not warn that responses may contain personal data or untrusted content. This increases the chance that integrators will ingest, display, or act on third-party content without appropriate sanitization, moderation, or privacy review.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: This line states 'Default: en' for the language filter on community posts, which indicates a locale-specific default. SQP-3 applies because the documentation does not mention user opt-in, language selection, or a region-specific reason for enforcing English by default.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file shows curl examples that require placing an API key in the X-CMC_PRO_API_KEY header, but it does not include any warning that the value is a credential and should be handled carefully. For markdown files, missing warnings about behaviours affecting privacy or system integrity are in scope, and exposing credential usage in copy-paste examples benefits from a brief caution.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The later example again instructs users to send an API key in an HTTP header but provides no accompanying warning about protecting secrets. Repeated credential-bearing examples in documentation should include at least a brief disclosure so users understand the privacy and security implications.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file includes curl examples that require an X-CMC_PRO_API_KEY header, which involves handling a credential, but the document provides no warning about keeping the key secret or avoiding accidental exposure in shell history, screenshots, or shared logs. Under the markdown-specific warning criterion, credential-related behavior should be disclosed when it could affect privacy or account security.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The example for the CMC100 latest endpoint again instructs users to send a live API credential in a request header, but the surrounding documentation does not warn about sensitive credential handling. This omission may lead users to expose account secrets while following the example.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown example requires an API key in the request header but does not disclose that the key is sensitive or that careless use could expose account access. For markdown guidance that affects privacy or account integrity, a warning should be present.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The final endpoint example also uses the X-CMC_PRO_API_KEY header without any adjacent warning about secret handling. Repeating credential-using examples without a disclosure increases the chance users will treat the key as non-sensitive.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: This markdown file includes curl examples that require an X-CMC_PRO_API_KEY header, but it does not warn users not to expose, hardcode, or share their API key. For markdown files, omission of warnings about behaviors affecting privacy or system integrity can be relevant, and credential handling is a user-impacting concern.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The curl examples show an API key header placeholder without warning that real keys entered directly on shared terminals, in shell history, CI logs, or screen recordings can be exposed. While the example does not hardcode a real secret, documentation that normalizes direct command-line secret entry increases the chance of credential leakage in operational use.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The API key info documentation describes plan limits, rate limits, and usage metadata but omits any note that these details can be sensitive operational information. If such outputs are casually shared in tickets, logs, or screenshots, they can reveal service capacity, consumption patterns, and account characteristics useful for reconnaissance or abuse planning.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.