Security audit

check-hymx-transaction

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a narrow Hymatrix bridge transaction lookup and does not show hidden, persistent, destructive, or credential-seeking behavior.

Install only if you are comfortable with transaction hashes you provide being sent to Hymatrix's bridge scan API. The skill appears narrow and non-persistent, but its trigger wording and outbound-data disclosure could be clearer.

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
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.
md
command: node script/index.js

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill declares a command (node script/index.js) that likely performs network access, but the manifest does not specify any permissions or allowed-tools boundary. This creates an authorization ambiguity where an agent or runtime may execute network-capable code without an explicit least-privilege declaration, making review and containment harder.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger says to use the skill when the user provides a transaction ID or hash and asks for 'the following information,' but it does not enumerate concrete trigger phrases, supported question types, or exclusion cases. This broad wording can cause unintended invocation for general transaction-related questions that mention a hash without clearly requesting a bridge-status lookup.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The natural-language instructions are written as mandatory Chinese guidance to the agent and do not indicate that the user may choose another language. This creates a locale/language policy concern because the skill appears to assume or enforce a specific language without opt-in or justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This code sends the user-provided transaction identifier to an external API endpoint, which is a network operation involving user data. There is no confirmation prompt, logging, comment explaining the disclosure, or other visible user warning in this file about the outbound request.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.