ClawHub
Back to skill

Security audit

Hermes Minimax Oauth

Security checks for vulnerabilities and agentic risk

Overview

This skill documents MiniMax OAuth support for Hermes in a coherent and disclosed way, with expected token storage and API use.

Install only if you intend to add MiniMax OAuth support to Hermes. After login, protect ~/.hermes/auth.json because it contains OAuth credentials that may allow MiniMax account access within the documented scopes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file documents a security-relevant behavior: the OAuth access token is stored in ~/.hermes/auth.json. Although the behavior is described, there is no user-facing warning about local credential persistence, file sensitivity, or the need to protect that file, which can affect user privacy and account security.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- Client ID: `78257093-7e40-4613-99e0-527b14b39113`
- Scope: `group_id profile model.completion`
- Inference URL: `https://api.minimax.io/v1` (global) / `https://api.minimaxi.com/v1` (CN)

## 注意事项

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- Client ID: `78257093-7e40-4613-99e0-527b14b39113`
- Scope: `group_id profile model.completion`
- Inference URL: `https://api.minimax.io/v1` (global) / `https://api.minimaxi.com/v1` (CN)

## 注意事项

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language instructions throughout the file are presented in Chinese only, which can constitute a language/locale policy issue when no user opt-in or alternative language is offered. The file does not indicate that the skill is region-specific documentation or that Chinese is required for a justified compliance reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.