Back to skill

Security audit

bocha-web-search-whalecloud

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese web search integration that sends user search queries to a documented Whalecloud/Bocha API using a configured token.

Install this only if you are comfortable sending search queries to Whalecloud's Bocha proxy and storing WHALECLOUD_API_KEY in the skill environment. Do not use it for searches containing secrets or sensitive personal data, and prefer tighter activation rules if you want to avoid unnecessary external searches.

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
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill requires environment access to a sensitive API token and performs networked search requests, but it does not declare an explicit tool scope such as allowed-tools or permissions. That increases the chance the runtime grants broader-than-necessary capabilities or invokes the skill without clear confinement, which is a least-privilege failure rather than a direct exploit by itself.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger description is broad enough to match many common requests involving Chinese web content, fact verification, citations, news, companies, products, and any mention of Bocha. Over-triggering can cause unnecessary network access and increase exposure of sensitive user queries to the external search provider, especially because the skill uses an API-backed remote service.

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 · references/api-spec.md (reported line 56)May include surrounding context.

md
"totalEstimatedMatches": 10000000,
      "value": [
        {
          "id": "https://api.bochaai.com/v1/#WebPages.0",
          "name": "网页标题",
          "url": "https://example.com/article",
          "displayUrl": "https://example.com/article",

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file’s docstring, usage text, examples, error messages, and hints are all written only in Chinese, which imposes a specific language on all users. The policy for this category flags language/locale constraints when the skill does not provide an explicit language choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

标题和整份 API 规范均以中文固定表述,未说明这是面向特定中文用户群、区域场景,或是否提供其他语言版本。根据规则,强制单一语言而无用户选择或明确业务限定,属于自然语言层面的语言/区域策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.