ClawHub
Back to skill

Security audit

Zhipu Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Zhipu web-search helper that sends user search requests to the declared Zhipu API, with privacy cautions around queries and optional user IDs.

Install only if you are comfortable sending search queries to Zhipu/BigModel. Do not include secrets, private internal text, or personal data in search queries, and omit user_id or use a pseudonymous value unless you specifically need it.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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)

Tainted flow: 'headers' from os.environ.get (line 81, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
"Content-Type": "application/json",
    }
    
    response = requests.post(
        f"{API_BASE_URL}/chat/completions",
        headers=headers,
        json=payload,
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill requires an API key from the environment and is explicitly designed to perform web searches, which implies network access, but it does not declare any tool scope such as permissions or allowed-tools. This weakens least-privilege controls and makes the skill harder to sandbox or review, increasing the risk of unintended outbound access or misuse if the skill is invoked in a broader agent environment.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill documentation instructs users to provide a user_id and indicates it is an end-user identifier, but it does not include a privacy notice, purpose limitation, retention guidance, or warning that this identifier may be transmitted to a third-party search provider. In a web-search skill, this is more dangerous because user queries and identifiers can be linked externally, creating privacy, compliance, and tracking risks.

External Transmission

Medium
Category
Data Exfiltration
Content
"Content-Type": "application/json",
    }
    
    response = requests.post(
        f"{API_BASE_URL}/chat/completions",
        headers=headers,
        json=payload,
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
92% confidence
Finding
The script sends the user-provided search query and optional user_id to an external third-party service, but the code provides no consent prompt, warning, redaction, or validation around what may be transmitted. In an agent-skill context, this can unintentionally disclose sensitive prompts, identifiers, or internal data if upstream callers pass secrets or personal data into the query or user_id fields.

Static analysis

No suspicious patterns detected.