ClawHub
Back to skill

Security audit

chukonu-web-search

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently configures a remote OAuth-protected search and research MCP service, with sensitive token handling explicitly cautioned rather than abused.

Before installing, consider that your searches and research objectives will be sent to the Chukonu remote MCP service. Use the normal OAuth flow, avoid static Authorization headers or API tokens, and treat legal or financial outputs as cited research with limitations rather than professional advice.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

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 40)May include surrounding context.

codex mcp list

text

在 Codex TUI 中用 `/mcp` 查看连接状态。若 OAuth 浏览器与 Codex 不在同一主机，先为 Codex 配置可回调的 `mcp_oauth_callback_url`，再登录；不要输出或持久化授权码、回调 URL、access token 或 refresh token。

不要为该服务器配置静态 `Authorization` 头或 `CHUKONU_SEARCH_API_TOKEN`。静态 Authorization 头会使 host 禁用 OAuth 回退，并可能导致 `401 invalid_token`。把 OAuth token 完全交给 host 保管，不要在日志、回答、示例或错误信息中泄露。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The primary skill description is written as a directive in Chinese and presents the skill as operating in that language context without stating that users may choose another language. Under the policy rule, forcing a specific language or locale without opt-in is a natural-language policy violation unless the constraint is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The instructions prescribe Chinese legal sources and Chinese-language filters as the expected mode of use, including examples with jurisdictions: ["CN"] and languages: ["zh"], but do not clarify whether this is optional or required by user intent. This can be read as imposing a locale/language constraint rather than offering it as a selectable context.

Content

No source excerpt is available for this finding.