Back to skill

Security audit

video-en2zh-dub

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the advertised video-dubbing workflow, but it under-discloses that subtitle content is sent to Microsoft's online edge-tts service despite claiming the components are offline.

Review this before installing if your videos contain confidential speech. Transcription is local, but the TTS stage uses Microsoft's online edge-tts service and may transmit the translated subtitle text; use an isolated environment and pinned dependencies if supply-chain reproducibility matters.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (17)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The title and opening description define the skill as turning English video into Chinese dubbed video, with no indication that users can choose another language or opt in to the locale constraint. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The README states the workflow is '全部离线/免费组件,不需要任何 API key', but later admits edge-tts depends on Microsoft's online service. This is a material misrepresentation of network and privacy behavior that could cause users to process sensitive media under a false assumption that no external service is involved.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill tells users to '只需要提供视频' and says the agent will automatically orchestrate the pipeline, but it does not warn that subtitle text and possibly sensitive spoken content derived from the video will be sent to an external Microsoft TTS service. In an agent context this is more dangerous because users may assume local-only processing and provide confidential recordings without informed consent.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill instructs the agent to read and write files in the working directory and inspect the runtime environment, but it does not declare an explicit tool scope such as permissions or allowed-tools. That creates a governance gap: an agent may access files or environment details more broadly than reviewers or policy tooling expect, increasing the risk of unintended data exposure or modification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description states the skill is used whenever a user wants to translate an English video into Chinese and specifically produces Chinese dubbing or Chinese/English dual audio. This hard-codes a Chinese language outcome rather than offering a language choice or documenting a justified locale restriction as a region-specific tool policy exception.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all operational guidance in Chinese, including troubleshooting and action steps, with no indication that the skill is region-specific or that users may choose another language. 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.

Tainted flow: 'value' from os.environ.get (line 141, credential/environment) → open (file write)

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/check_env.py (reported line 147)May include surrounding context.

python
return

    try:
        with open(value, "a"):
            pass
        print(f"  OK    SSLKEYLOGFILE {value}(实测可写)")
        return

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This file's docstring, CLI help text, and runtime messages are entirely in Chinese, which imposes a specific language on users. Under the policy, language constraints should be opt-in or clearly justified as region-specific; that is not stated here.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all operational guidance only in Chinese, with no opt-in, alternative language, or justification that the skill is region-specific, which can force a specific language on users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The top comment is written as a directive-style project note in Chinese ('Python 依赖,推荐安装顺序见文件末尾'), and the rest of the instructional comments are also Chinese-only. For a natural-language policy review, this can be a locale/language constraint because the file provides user-facing setup guidance in a single language without any opt-in or stated regional limitation.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

Using a lower-bounded but unpinned dependency for openai-whisper allows future releases to be installed without review, which can introduce breaking changes or vulnerable/transitively compromised packages into the build. In a media-processing skill that relies on heavyweight third-party ML and audio tooling, supply-chain risk is higher because many transitive dependencies may be pulled at install time.

Content

Scanner excerpt · requirements.txt (reported line 3)May include surrounding context.

text
# Python 依赖,推荐安装顺序见文件末尾

openai-whisper>=20230124
edge-tts>=7.0.0
pysrt>=1.1.2
pydub>=0.25.1

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The edge-tts dependency is specified with >=7.0.0, so any newer release can be installed automatically. That creates a supply-chain exposure where unreviewed upstream changes, vulnerable releases, or compromised publishing events could affect the environment running this skill.

Content

Scanner excerpt · requirements.txt (reported line 4)May include surrounding context.

text
# Python 依赖,推荐安装顺序见文件末尾

openai-whisper>=20230124
edge-tts>=7.0.0
pysrt>=1.1.2
pydub>=0.25.1

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

An unpinned pysrt version permits installation of future releases that may contain security defects or disruptive behavior changes. While this package is less inherently risky than network-facing components, it still contributes to overall supply-chain uncertainty in the build.

Content

Scanner excerpt · requirements.txt (reported line 5)May include surrounding context.

text
openai-whisper>=20230124
edge-tts>=7.0.0
pysrt>=1.1.2
pydub>=0.25.1

# Python 3.13 起标准库移除了 audioop,而 pydub 依赖它。

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

Specifying pydub as >=0.25.1 allows later releases to be fetched automatically, which can introduce unreviewed code and transitive dependency changes. Because this skill processes untrusted media inputs and depends on ffmpeg-related workflows, dependency drift can increase the chance of exposing vulnerable parsing or command-invocation paths indirectly.

Content

Scanner excerpt · requirements.txt (reported line 6)May include surrounding context.

text
openai-whisper>=20230124
edge-tts>=7.0.0
pysrt>=1.1.2
pydub>=0.25.1

# Python 3.13 起标准库移除了 audioop,而 pydub 依赖它。
# 在 3.13+ 上不装这个包,import pydub 会直接失败。

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains its primary documentation and runtime output entirely in Chinese, which imposes a specific language on users without any opt-in or alternative. The policy explicitly flags language or locale constraints when a skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring, CLI description, help text, and runtime messages are all written in Chinese, which imposes a specific language on users. The file does not offer any user-facing language/locale option or explain that the tool is intentionally limited to Chinese-speaking users, so this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.