ClawHub
Back to skill

Security audit

minimax-video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MiniMax video-generation client that uses the user's MiniMax API key, sends generation inputs to MiniMax, and can save generated videos locally.

Install only if you are comfortable sending prompts, image URLs, and related generation metadata to MiniMax using your MINIMAX_API_KEY. Set MINIMAX_REGION intentionally, and choose output paths carefully because generated videos can be written to local disk.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented behavior exceeds the declared purpose and omits important operational capabilities such as task polling, standalone file retrieval/download, credential use, and external network communication. This mismatch is dangerous because users may invoke the skill under incomplete assumptions, leading to unexpected data disclosure to third parties, silent file downloads, or broader runtime permissions than intended.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill documents use of environment secrets and external network access but does not declare any tool scope or permissions boundaries. That creates a real security governance gap: users and hosting agents cannot accurately understand or constrain what the skill is allowed to access, increasing the chance of unintended secret use or network exfiltration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill accepts prompts and image URLs for API-driven processing but does not warn that this content is transmitted to an external service. In practice, users may supply sensitive text or private media, and the lack of disclosure increases the risk of unintentional third-party data exposure.

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 · references/api.md (reported line 5)May include surrounding context.

md
# API 配置
BASE_URL_CN = "https://api.minimaxi.com/v1"
BASE_URL_INT = "https://api.minimax.io/v1"

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/video.py (reported line 17)May include surrounding context.

python
# API 配置
BASE_URL_CN = "https://api.minimaxi.com/v1"
BASE_URL_INT = "https://api.minimax.io/v1"

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 · references/api.md (reported line 6)May include surrounding context.

md
# API 配置
BASE_URL_CN = "https://api.minimaxi.com/v1"
BASE_URL_INT = "https://api.minimax.io/v1"


def get_base_url() -> str:

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/video.py (reported line 18)May include surrounding context.

python
# API 配置
BASE_URL_CN = "https://api.minimaxi.com/v1"
BASE_URL_INT = "https://api.minimax.io/v1"


def get_base_url() -> str:

Tainted flow: 'params' from requests.post (line 176, network 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/video.py (reported line 178)May include surrounding context.

python
url = f"{get_base_url()}/query/video_generation"
    params = {"task_id": task_id}

    response = requests.get(url, headers=get_headers(), params=params, timeout=30)
    response.raise_for_status()

    return response.json()

Tainted flow: 'params' from requests.post (line 176, network 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/video.py (reported line 260)May include surrounding context.

python
url = f"{get_base_url()}/query/video_generation"
    params = {"task_id": task_id}

    response = requests.get(url, headers=get_headers(), params=params, timeout=30)
    response.raise_for_status()

    return response.json()

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill says videos are automatically downloaded and saved locally but does not clearly warn users before local file creation occurs. In an agent context, undeclared local writes can surprise users, overwrite files, consume disk space, or leave sensitive/generated content on disk without explicit consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The API reference instructs users to send prompts and image URLs to third-party MiniMax endpoints, but it does not warn that user content and referenced media will leave the local environment and be processed externally. In a media-generation skill, prompts and images may contain sensitive, proprietary, or personal data, so the omission creates a real privacy and informed-consent risk even if it is not an exploit by itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The base URL selection defaults to the China region when MINIMAX_REGION is unset, which imposes a locale/region choice implicitly rather than letting the user opt in. This matches the policy concern around forcing a specific language or locale without explicit user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.