ClawHub
Back to skill

Security audit

ZhiPu Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Zhipu web-search helper that sends user search terms to Zhipu using a configured API key, with no hidden persistence or unrelated local access found.

Install this only if you are comfortable sending your search queries to Zhipu's Web Search API and providing a Zhipu API key. Prefer the ZHIPU_API_KEY environment variable over config.json, and do not put unrelated secrets in the skill directory.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill documentation instructs users to provide and use a sensitive environment variable (ZHIPU_API_KEY), and explicitly notes that the skill reads it at runtime, but the skill declares no permissions or allowed-tools scope. That mismatch weakens least-privilege controls and transparency: a host may not clearly understand that the skill needs environment access, increasing the chance of unintended secret exposure or over-broad execution rights.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code sends the user's search query to a third-party web API and includes a bearer token in the request, but there is no confirmation prompt or explicit user-facing notice that the query will be transmitted off-system. The top comment describes the API call for developers, but it does not function as a user disclosure about privacy or external data sharing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file's natural-language strings and usage messages are entirely in Chinese, including error output and usage guidance, with no indication that this skill is intentionally region-specific or that users can opt into another language. That creates a language/locale policy concern under the requirement to avoid forcing a specific language without user choice or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.