Back to skill

Security audit

Qwen Video Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its video-generation purpose, but it needs review because it sends prompts to an external provider and downloads provider-supplied URLs without strong network or size controls.

Install only if you are comfortable sending prompts to Alibaba Cloud DashScope and storing generated videos locally. Use a dedicated DashScope key with limited scope where possible, avoid secrets or sensitive personal data in prompts, set a controlled output directory, and review or patch the download code before using it in sensitive or shared environments.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/generate_video.py:269
Finding

Unvalidated Server-Provided Video URL Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/generate_video.py:160
Finding

Unbounded Downloads and Missing Network Timeouts Allow Resource Exhaustion

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (7)

Tainted flow: 'headers' from os.environ.get (line 152, credential/environment) → requests.post (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/generate_video.py (reported line 133)May include surrounding context.

python
}
    }
    
    response = requests.post(API_URL, headers=headers, json=payload)
    
    if response.status_code != 200:
        print(f"❌ 提交任务失败: {response.status_code}", file=sys.stderr)

Tainted flow: 'headers' from os.environ.get (line 152, credential/environment) → requests.get (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/generate_video.py (reported line 156)May include surrounding context.

python
"Authorization": f"Bearer {api_key}"
    }
    
    response = requests.get(f"{TASK_QUERY_URL}{task_id}", headers=headers)
    
    if response.status_code != 200:
        return None, f"查询失败: {response.status_code}"

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill appears to use environment variables, network access to a cloud API, and shell/Python execution, but it does not declare any explicit tool scope or permissions. This weakens least-privilege controls and makes it easier for the skill to be invoked with broader capabilities than users or the platform may expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation guidance is broad enough to match many ordinary requests about videos or visualization, which can cause the skill to trigger in situations where the user did not intend to send content to an external service. In this context, over-triggering is more concerning because prompts may contain sensitive data and the skill produces files on disk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation does not warn that user prompts are transmitted to an external cloud video-generation provider and that generated outputs are persisted to local storage. This creates a privacy and data-handling risk because users may provide confidential prompts without understanding they will leave the local environment and create residual files.

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/generate_video.py (reported line 133)May include surrounding context.

python
}
    }
    
    response = requests.post(API_URL, headers=headers, json=payload)
    
    if response.status_code != 200:
        print(f"❌ 提交任务失败: {response.status_code}", file=sys.stderr)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and all CLI help/messages are written in Chinese, which effectively constrains the skill's user-facing behavior to a specific language. The file does not offer any opt-in, locale selection, or documented justification for this language restriction.

Content

No source excerpt is available for this finding.