Back to skill

Security audit

Baidu Nearby / 百度能力集合

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Baidu search and maps helper that sends user-provided queries and locations to Baidu, with no hidden persistence or destructive behavior found.

Install only if you are comfortable sending search terms, addresses, coordinates, and your Baidu API key to Baidu services. Avoid using it for highly sensitive locations unless that external sharing is acceptable.

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 (11)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill declares use of sensitive capabilities via environment credentials and external network access, but it does not explicitly constrain or document tool scope with permissions or allowed-tools. That mismatch can lead to overbroad runtime access and weaker governance, making it harder for a platform to enforce least privilege or for reviewers to understand what the skill is permitted to do.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation guidance is broad enough to match many generic requests involving web search, travel planning, or nearby recommendations. Overly broad triggering can cause the skill to activate unexpectedly, sending user queries or location-related input to external services when a more specific skill selection step would be safer.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code constructs an HTTP request containing the user's address data and transmits it to an external service for geocoding. While the network call is part of the tool's purpose, the file lacks any disclosure in usage text, comments, or prompts that entered locations will be sent to Baidu's servers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/baidu_direction.py (reported line 163)May include surrounding context.

python
return None
    
    url = (
        f"https://api.map.baidu.com/geocoding/v3/?"
        f"address={urllib.parse.quote(address)}"
        f"&output=json&ak={ak}"
    )

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/baidu_direction.py (reported line 244)May include surrounding context.

python
return None
    
    url = (
        f"https://api.map.baidu.com/geocoding/v3/?"
        f"address={urllib.parse.quote(address)}"
        f"&output=json&ak={ak}"
    )

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/baidu_nearby.py (reported line 215)May include surrounding context.

python
return None
    
    url = (
        f"https://api.map.baidu.com/geocoding/v3/?"
        f"address={urllib.parse.quote(address)}"
        f"&output=json&ak={ak}"
    )

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/baidu_nearby.py (reported line 259)May include surrounding context.

python
return None
    
    url = (
        f"https://api.map.baidu.com/geocoding/v3/?"
        f"address={urllib.parse.quote(address)}"
        f"&output=json&ak={ak}"
    )

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/baidu_nearby.py (reported line 328)May include surrounding context.

python
return None
    
    url = (
        f"https://api.map.baidu.com/geocoding/v3/?"
        f"address={urllib.parse.quote(address)}"
        f"&output=json&ak={ak}"
    )

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The request header hard-codes Accept-Language: zh-CN,zh;q=0.9,en;q=0.8, which imposes a specific language/locale preference. Under the policy, locale constraints should either be user-selectable or clearly justified as region-specific; this file does not provide such opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The function reads BAIDU_API_KEY or BAIDU_AK from the environment, which is access to sensitive credential material. The code avoids printing the key, but there is no explicit user-facing warning or documentation in this file that the tool depends on and reads credentials from environment variables.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file contains user-facing documentation, usage text, and runtime messages only in Chinese, which imposes a specific language on all users. Under the policy, forcing a language without an explicit choice or justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.