ClawHub
Back to skill

Security audit

百度智能云VOD视频翻译

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real Baidu Cloud video translation skill, but it needs Review because it uploads user media to cloud services and uses cloud/netdisk authority with weak disclosure and URL scoping.

Review before installing. Use this only for media you are comfortable sending to Baidu Cloud VOD and, if enabled, Baidu Netdisk. Use least-privileged Baidu credentials, do not paste AK/SK values into chat or files, watch for paid processing charges, and be careful with delete-project or update-task operations.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/common.py:677
Finding

Unvalidated Remote Result URL Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (21)

Tainted flow: 'upload_url' from os.environ.get (line 263, credential/environment) → requests.put (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/common.py (reported line 231)May include surrounding context.

python
headers = {"Content-Type": "video/mp4"}
    with open(video_path, 'rb') as f:
        response = requests.put(upload_url, data=f, headers=headers, timeout=600)
    
    if response.status_code in [200, 100]:
        if debug:

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description emphasizes translation features but does not clearly warn users that video, audio, subtitle, and possibly biometric voice content will be uploaded to and processed by a third-party cloud service. Because this skill handles potentially sensitive media, lack of explicit disclosure undermines informed consent and can lead to unintentional exposure of private or regulated data.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 303)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 312)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 321)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 330)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 412)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 419)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 426)May include surrounding context.

md
python3 scripts/translate.py <视频> --source zh --target en

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

This skill performs multiple outbound network operations to Baidu VOD and downloads arbitrary result URLs, yet the declared permissions apparently do not include network access. Undeclared network capability is a real security concern because it enables data exfiltration, remote task creation, and cloud-side actions without transparent user consent.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

This skill performs multiple outbound network operations to Baidu VOD and downloads arbitrary result URLs, yet the declared permissions apparently do not include network access. Undeclared network capability is a real security concern because it enables data exfiltration, remote task creation, and cloud-side actions without transparent user consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger rules include broad phrases such as requests to 'translate video', 'video dubbing', and especially 'query or manage translation projects/tasks', without strong scoping to explicit user intent or this specific cloud provider workflow. Overbroad triggering can cause the skill to activate in unrelated contexts and prompt for local file paths or begin cloud-processing workflows the user did not intend, increasing privacy and consent risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to export BAIDU_VOD_AK and BAIDU_VOD_SK credentials and shows concrete secret-handling patterns, but it does not warn against exposing those values in chat, logs, shell history, or generated command output. This creates a realistic risk of credential leakage, especially in agent-mediated environments where commands and transcripts may be retained.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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/common.py (reported line 190)May include surrounding context.

python
if method == "GET":
        response = requests.get(url, headers=headers, params=params, timeout=30)
    elif method == "POST":
        response = requests.post(url, headers=headers, json=json_data, timeout=30)
    elif method == "PUT":
        response = requests.put(url, headers=headers, json=json_data, timeout=30)
    else:

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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/common.py (reported line 192)May include surrounding context.

python
elif method == "POST":
        response = requests.post(url, headers=headers, json=json_data, timeout=30)
    elif method == "PUT":
        response = requests.put(url, headers=headers, json=json_data, timeout=30)
    else:
        raise ValueError(f"不支持的 HTTP 方法: {method}")

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/common.py (reported line 602)May include surrounding context.

python
def check_bdpan_installed():
    """检查 bdpan 是否安装"""
    try:
        result = subprocess.run(
            ["bdpan", "version"],
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/common.py (reported line 616)May include surrounding context.

python
def check_bdpan_logged_in():
    """检查 bdpan 是否已登录"""
    try:
        result = subprocess.run(
            ["bdpan", "whoami"],
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/common.py (reported line 633)May include surrounding context.

python
if debug:
        print(f"执行: {' '.join(cmd)}")
    
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=600)
    
    if result.returncode == 0:
        if debug:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/common.py (reported line 651)May include surrounding context.

python
if debug:
        print(f"执行: {' '.join(cmd)}")
    
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=600)
    
    if result.returncode == 0:
        if debug:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/common.py (reported line 666)May include surrounding context.

python
def list_netdisk_files(path="", debug=False):
    """列出网盘文件"""
    cmd = ["bdpan", "ls", path, "--json"]
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
    
    if result.returncode == 0:
        try:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The module docstring, usage instructions, and all descriptive text are presented only in Chinese. This creates a locale/language policy issue because users are not offered a language choice or an alternative locale, and the file does not document a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.