ClawHub
Back to skill

Security audit

三剪客 · 全能视频生成

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed a7w video API client, but it includes a broader generic client that can use the same API key to inspect and call unrelated a7w plugins.

Review this before installing if you only want a narrow full_video helper. Use a limited a7w API key if possible, avoid setting --host or A7W_HOST unless you trust the destination, and be aware the client can enumerate and call more than the two video endpoints shown in the skill overview.

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
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (17)

Tainted flow: 'req' from os.environ.get (line 151, credential/environment) → urllib.request.urlopen (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/client.py (reported line 111)May include surrounding context.

python
headers["Content-Type"] = "application/json"
    req = urllib.request.Request(url, data=data, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, timeout=timeout) as resp:
            raw = resp.read().decode("utf-8", "replace")
            status = resp.status
    except urllib.error.HTTPError as exc:

Tainted flow: 'req' from os.environ.get (line 151, credential/environment) → urllib.request.urlopen (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/client.py (reported line 153)May include surrounding context.

python
headers["Content-Type"] = "application/json"
    req = urllib.request.Request(url, data=data, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, timeout=timeout) as resp:
            raw = resp.read().decode("utf-8", "replace")
            status = resp.status
    except urllib.error.HTTPError as exc:

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared purpose is narrowly framed as a full-video generation skill, but the bundled client reportedly supports generic access to arbitrary a7w plugins, schema enumeration/export, local credential storage, and points/task inspection. This mismatch is dangerous because it obscures the real execution surface and can trick users or agents into authorizing a much more powerful integration than intended.

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 5)May include surrounding context.

md
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.

md
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
77% confidence
Finding

The skill advertises and appears to include code-capable operations (environment access, file read/write, network, shell) but does not declare any explicit tool scope or permission boundaries. That creates an avoidable over-privilege risk: an agent or reviewer may assume a narrow video-generation skill while the packaged client can perform broader local and network actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · README.md (reported line 11)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · README.md (reported line 95)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · README.md (reported line 104)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 5)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 7)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 35)May include surrounding context.

md
name: full-video
slug: full-video
displayName: 三剪客 · 全能视频生成
description: "支持文生视频、首尾帧视频生成及多模态参考视频生成。支持 提交任务、查询任务。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
version: 1.0.6
summary: "「全能视频生成」的完整调用封装：2 个接口的官方文档、参数表与一个零依赖客户端。包内含完整操作文档与零依赖客户端（`SKILL.md` + `references/`）。需要自备 api.a7w.cn 的 API Key，注册领 Key 见 https://api.a7w.cn/ 。遇到问题可加技术微信 9872659。"
license: MIT

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is described as supporting video task submission and query, but the bundled client is a generic plugin-market client that can enumerate all apps, inspect schemas, and invoke arbitrary APIs. In an agent setting, this broader-than-advertised capability increases the risk of unintended access, prompt-scope violation, and misuse of the user's API key against unrelated services.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The dump command exports schemas for all available plugins, which exceeds the stated submit/query behavior for a video-generation skill. In context, this can facilitate mass discovery of unrelated APIs and capabilities accessible with the same key, expanding attack surface and enabling overbroad agent actions beyond user expectation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The user-facing guidance section is written entirely in Chinese, which can impose a language constraint on users without stating that the skill is Chinese-only or offering an alternative language. This is a natural-language policy concern because the file includes operational instructions but does not provide any language choice or justification for the locale restriction.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

In this markdown/manifest content, the description and summary explain capabilities but do not define any precise trigger phrases, activation boundaries, or exclusion conditions. Without explicit scope constraints, a host system could match the skill too broadly when users ask generally about video generation or task querying.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The top-level usage text says whoami verifies the key and shows account and balance, and points checks balance. In code, cmd_whoami only validates the key by listing apps and explicitly notes there is no public account/balance API, while cmd_points merely sums recent task usage as a reference rather than retrieving an actual balance. This is an active contradiction between documentation and behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.