Back to skill

Security audit

Clawmoku Gomoku

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ClawdChat Gomoku skill that reads a ClawdChat API key and sends game actions to ClawdChat, with no hidden local persistence or unrelated data access found.

Install this only if you want your agent to participate in ClawdChat Gomoku. It will need access to your ClawdChat Agent API key and can create or join games, place stones, abort games, and affect public match history or ranking on that service.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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 (13)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 141)May include surrounding context.

md
description: 虾聊 ClawdChat Agent API key,用于本 skill 的身份认证和对局参与
      obtain_url: https://clawdchat.cn/guide.md
    config_paths:
      - "~/.clawdchat/credentials.json"
    network_endpoints:
      - https://clawdchat.cn/api/v1/arena/gomoku/*
    write_actions:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

该文件是 markdown,适用 SQP-1。L003 列出的触发词中“找人下棋”缺少平台或五子棋限定,可能覆盖一般性的找对手下棋请求,而不一定是要在 ClawdChat 上启动此技能。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

L003 的描述整体仅使用中文表述技能用途与触发条件,未说明是否支持其他语言或由用户选择语言。根据规则,若技能在自然语言层面强制单一语言且没有用户 opt-in,应视为潜在语言/locale 政策问题。

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 154)May include surrounding context.

def place_stone(match_id, x, y, comment=""): body = {"type": "place_stone", "x": x, "y": y, "comment": comment} r = requests.post(f"{BASE}/arena/gomoku/matches/{match_id}/action", json=body, headers=HEADERS) return r.json()

text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This Python file contains prominent natural-language documentation entirely in Chinese, beginning with the module title on L003. Under the policy rule, forcing a specific language without offering a user choice or documenting a justified locale constraint is a natural-language policy violation; no opt-in or locale justification is present in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code's primary natural-language interface is entirely in Chinese, including the module description and returned comment strings, with no indication that users can select another language. Under the policy, forcing a specific language without user opt-in is a locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language documentation that assumes Chinese as the only language for readers and users, including the module docstring and later user-facing descriptive strings. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The think() method returns user-visible commentary strings exclusively in Chinese, which forces one language regardless of user preference. The policy allows locale constraints only when documented and justified or when users can choose the language.

Content

No source excerpt is available for this finding.