ClawHub
Back to skill

Security audit

百度AI搜索（千帆）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu AI search wrapper that sends the user's query to Baidu and returns an AI summary with references.

Install only if you are comfortable sending search queries to Baidu Qianfan using your BAIDU_API_KEY. Do not pass secrets, private documents, or sensitive personal data as search queries.

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)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The natural-language instructions and usage guidance are entirely in Chinese, which effectively forces a specific language for users without any opt-in or alternative. The policy explicitly calls out language or locale constraints as violations unless the skill offers a choice or clearly documents a justified regional limitation.

External Transmission

Medium
Category
Data Exfiltration
Content
"Content-Type": "application/json"
    }

    response = requests.post(url, json=request_body, headers=headers, timeout=120)
    response.raise_for_status()
    result = response.json()
Confidence
80% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This code sends the user's query and request metadata to Baidu's external AI search endpoint via an HTTP POST request. While the module docstring names the API, there is no runtime warning, confirmation, or explicit user-facing disclosure that user-provided content will be transmitted off-system.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The file's natural-language description and several comments are written only in Chinese, which can impose a language assumption on users without opt-in or explanation. Under the policy, language constraints should either be optional for the user or clearly documented as intentional and justified.

Static analysis

No suspicious patterns detected.