Security audit

Cmc Api Crypto

Security checks for vulnerabilities and agentic risk

Overview

This is a CoinMarketCap API reference skill with purpose-aligned examples and no hidden execution, persistence, or data access beyond user-supplied API calls.

Installers should treat this as a documentation skill. Use your CoinMarketCap API key only when intentionally making requests, prefer an environment variable or secret manager over pasting keys into shared scripts or logs, and verify that CoinMarketCap is the API you intended when the skill activates for generic crypto data questions.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger text is broad enough to activate this skill for generic cryptocurrency/API questions, making skill selection less precise and increasing the chance the agent invokes it outside its narrow intended scope. Overbroad routing can cause unintended tool availability or irrelevant instructions to be loaded, which is a real security and reliability concern even though the content itself is only documentation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file includes curl examples that require users to supply an X-CMC_PRO_API_KEY header, but it does not warn users to protect the credential or avoid exposing it in shared shells, logs, or screenshots. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect privacy or sensitive data handling.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The historical listings example again instructs users to send an API key in an HTTP header but provides no warning that the value is sensitive. Repeated credential-use examples in documentation should disclose safe handling expectations when they may affect user privacy or account security.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown example shows authenticated API access but does not warn readers that the API key is sensitive account data. Under SQP-2 for markdown, missing warnings about privacy- or credential-affecting behavior are reportable when omitted from the skill description.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown file includes curl examples that require an X-CMC_PRO_API_KEY header, but the surrounding documentation does not warn users that they are handling a secret credential. For markdown files, exposing behavior that affects privacy or account integrity should include a brief warning about safeguarding keys and avoiding accidental disclosure in shared terminals, logs, or screenshots.
Content: No source excerpt is available for this finding.