Back to skill

Security audit

address2lnglat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu Maps geocoding helper that sends user-provided location queries to Baidu and saves the returned coordinates locally.

Install only if you are comfortable sending your search terms, addresses, and Baidu AK to Baidu Maps. Use a virtual environment for dependencies, avoid privileged installs, and treat exported CSV files as untrusted third-party data when opening them in spreadsheet apps.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/geocoder.py:210
Finding

CSV Formula Injection Through Unsanitized API Response Fields

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:42
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
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 (9)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly describes making outbound Baidu API requests and saving results to CSV/JSON, but the manifest does not declare any tool scope or permissions for network and file-write behavior. This weakens user and platform transparency, making it easier for a skill to exfiltrate user-supplied data or write unexpected local artifacts without clear upfront consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow sends user-provided keywords/addresses and an AK-authenticated request to Baidu's external API, then stores returned data locally in CSV/JSON, but the skill text does not clearly warn users about this data transfer and retention. This creates a privacy and data-handling risk, especially if users submit sensitive locations or proprietary lists of places.

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/geocoder.py (reported line 54)May include surrounding context.

python
print(f"\n🌐 正在搜索「{keyword}」相关地点...\n")

    url = "https://api.map.baidu.com/place/v2/search"
    results = []
    page_num = 0

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/geocoder.py (reported line 155)May include surrounding context.

python
print(f"\n🌐 正在搜索「{keyword}」相关地点...\n")

    url = "https://api.map.baidu.com/place/v2/search"
    results = []
    page_num = 0

Tainted flow: 'params' from input (line 59, user input) → requests.get (network output)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/geocoder.py (reported line 71)May include surrounding context.

python
}

        try:
            resp = requests.get(url, params=params, timeout=10)
            data = resp.json()
        except Exception as e:
            print(f"  ⚠️  第 {page_num + 1} 页请求失败:{e}")

Tainted flow: 'geo_params' from input (line 156, user input) → requests.get (network output)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/geocoder.py (reported line 158)May include surrounding context.

python
geo_url = "https://api.map.baidu.com/geocoding/v3/"
            geo_params = {"address": address or name, "output": "json", "ak": ak}
            try:
                resp = requests.get(geo_url, params=geo_params, timeout=10)
                geo_data = resp.json()
            except Exception as e:
                print(f"  [{i:02d}/{len(place_list)}] {name}")

Tainted flow: 'csv_file' from input (line 290, user input) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/geocoder.py (reported line 207)May include surrounding context.

python
json_file = f"lnglat_{safe}.json"

    # CSV
    with open(csv_file, "w", encoding="utf-8-sig", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=[
            "序号", "名称", "详细地址", "BD-09经度", "BD-09纬度", "坐标来源", "类型", "置信度", "状态"
        ])

Tainted flow: 'json_file' from input (line 290, user input) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/geocoder.py (reported line 226)May include surrounding context.

python
})

    # JSON
    with open(json_file, "w", encoding="utf-8") as f:
        json.dump(results, f, ensure_ascii=False, indent=2)

    return csv_file, json_file

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module description and user-facing usage instructions are entirely in Chinese, and the interactive prompts throughout the script follow the same pattern. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.