Back to skill

Security audit

AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its digital-human video purpose, but its bundled client can use a paid API key for broader a7w access and arbitrary host overrides, so it should be reviewed before installing.

Install only if you are comfortable sending photo/face and voice/audio material to the a7w cloud service and have consent for any likeness or voice used. Keep the default api.a7w.cn host, avoid --host or A7W_HOST unless you fully trust the endpoint, prefer temporary environment credentials over saved login for agents, and restrict agent use to image_human submit/query rather than the generic app, dump, or arbitrary call commands.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (22)

Tainted flow: 'req' from os.environ.get (line 151, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
93% confidence
Finding

The request destination is influenced by the user-controlled A7W_HOST environment variable or CLI --host and then used directly in urllib.request.urlopen while attaching the Bearer API key. This creates an SSRF-style exfiltration risk: a user or calling agent can be induced to send the stored credential to an attacker-controlled host over HTTPS without validation.

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
93% confidence
Finding

The bulk schema-dump path uses the same unvalidated host selection and sends authenticated requests to whatever host is provided via environment/config/CLI. Because request_soft is used repeatedly across app enumeration, a malicious host can harvest the API key and potentially collect additional metadata from many authenticated requests.

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:
            return json.loads(resp.read().decode("utf-8", "replace")), resp.status
    except urllib.error.HTTPError as exc:
        raw = exc.read().decode("utf-8", "replace")

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a narrowly scoped image-human video generator, but the referenced client behavior appears to support generic listing of apps, schema inspection, arbitrary API invocation, task querying, bulk schema export, and local API key persistence. That scope expansion materially increases attack surface because a user invoking a seemingly single-purpose skill could be induced to access unrelated remote capabilities or expose locally stored credentials.

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
辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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.c

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
辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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.c

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs users to upload a facial image and voice recording to an external API, but it does not warn about privacy, consent, biometric/voice sensitivity, retention, or third-party processing. Because the inputs are highly sensitive personal data that can enable impersonation or deepfake generation, the absence of clear consent and privacy guidance materially increases user harm risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documentation is presented entirely in Chinese from the title onward, and it does not indicate that other languages are supported or that Chinese is required for a region-specific compliance reason. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding

The skill advertises and demonstrates capabilities that involve environment variables, local configuration files, network access, and a Python client, but it does not declare explicit permission boundaries. That makes it harder for a host platform or user to understand and constrain what the skill can access, increasing the risk of overbroad execution and credential exposure.

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 34)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 118)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 127)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 33)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 88)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 134)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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 144)May include surrounding context.

md
name: image-human
slug: image-human
displayName: AI数字人视频生成照片说话口播虚拟主播带货视频一键出片2K4K高清
description: "一张照片 + 一段录音,生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。四档清晰度可选,最低 0.015 元/秒,一条 60 秒口播视频最低 0.90 元。含完整参数表、分档计费口径与常见坑。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: 1.1.1
summary: "一张照片加一段录音,就能生成自然稳定的数字人口播视频——不用架机位、不用出镜、不用后期剪辑。支持 4 档清晰度(fast 快速 / standard 标准 / 2K 高清 / 4K 超清),按驱动音频时长计费,最低 1.5 点/秒(0.015 元/秒),一条 60 秒口播视频最低 0.90 元。适用于短视频口播矩阵号、电商带货讲解、知识科普、企业培训视频、课程讲师替身、虚拟主播、多语言版本批量生产、老照片复活与纪念视频等场景。含 submit / query 两个接口的完整参数表、mode 分档的真实计费口径(2K 是标准档的 2 倍、4K 是 4 倍)、图片与音频的入参要求、常见坑与排错,以及一个零依赖客户端。一个 Key 调用全部 AI 算力,不用自己部署 GPU,也不用同时管理几家的账单与配额。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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description and summary are broad marketing text and do not clearly define invocation boundaries, data flows, or operational limits. Ambiguous capability descriptions can mislead users and orchestrators into granting broader trust or permissions than intended, especially when the package also includes a generic client.

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 · SKILL.md (reported line 130)May include surrounding context.

}'

text

### 直接 curl

```bash
# 提交任务

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is presented as a dedicated image+audio human-video generator, but the bundled client is a generic marketplace client capable of calling any a7w plugin/API. This scope mismatch increases attack surface and can mislead users or agents into granting credentials to a tool with far broader capabilities than advertised.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The dump functionality enumerates all available plugins and exports their schemas, which is not necessary for a narrow image-human generation skill. In a credentialed environment, this enables broad service discovery and capability mapping that can be abused for reconnaissance, especially when paired with the generic call interface.

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 account and balance and points checks balance, but the implementation later states the gateway has no public account or balance endpoint. In practice, whoami only validates the key via /api/v1/apps, and points estimates spend from recent task usage rather than retrieving a true balance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.