Security audit

Hive Intelligence MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto data convenience layer for Hive's remote MCP endpoint, with no evidence of hidden execution, credential theft, or destructive behavior.

Install only if you want your agent to use Hive's remote crypto MCP service. Wallet addresses, token symbols, and other query inputs may be sent to Hive, so keep requests narrow and require explicit review before any write-like or transaction-related operation.

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

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

Medium

Confidence: 88% confidence
Finding: The default prompt advertises the skill as a broad crypto convenience layer for discovery and execution, which can cause overbroad routing of many unrelated or insufficiently scoped crypto requests into this skill. In an agent system, vague invocation boundaries increase the chance of unintended tool use, excessive capability exposure, and execution on ambiguous user intent.

Static analysis

No suspicious patterns detected.