Back to skill

Security audit

Douyin Super Agent

Security checks for vulnerabilities and agentic risk

Overview

This Douyin transcription skill is mostly purpose-aligned, but it automatically sends media to remote/cloud transcription integrations and writes transcript excerpts into persistent memory without clear per-run consent or controls.

Review this skill carefully before installing. Use it only if you are comfortable with audio/video content being processed by qwen-asr or Tencent Cloud when available, and with transcript excerpts being stored in a local memory-manager skill. Avoid sensitive meetings, private conversations, credentials, or regulated data unless remote ASR and memory storage are disabled or removed. Prefer pinned dependencies and an isolated environment for setup.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (4)

T02 · Agent Memory Poisoning

Error
Location
scripts/douyin.py:33
Finding

Untrusted transcription content is silently written to persistent Agent memory

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/douyin.py:63
Finding

Local audio may be delegated to remote ASR integrations without per-file consent

Content
View full analysis
10: return out.strip(), 'tencent-asr' return None, None ``` Remote Qwen processing is attempted before the local Whisper fallback: ```python def transcribe(path, prefer='qwen'): """三级降级: qwen-asr → whisper-medium → tencentcloud""" if prefer == 'qwen': text, eng = _qwen_asr(path) if text: log(f'✅ ASR: {eng}') return text, eng log('⬇️ qwen-asr 失败,降级到本地 whisper') text, eng = _whisper_local(path, 'medium') if text: log(f'✅ ASR: {eng}') return text, eng log('⬇️ 降级到腾讯云') return _tencent_asr(path) ``` ### Technical Analysis The default transcription path attempts the Qwen integration before local Whisper. A Tencent Cloud integration can also be invoked as a fallback. Both integrations are external Skills and receive the path to the selected local audio file. The external scripts are not included in this project, so the audit cannot verify: - Which remote endpoints receive the audio. - Whether transport security is enforced. - How credentials are obtained or protected. - Whether recordings are retained by the service. - Whether data is used f ...[truncated 1641 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
setup.sh:27
Finding

Installer resolves unpinned third-party dependencies in the active Python environment

Content
View full analysis
/dev/null || \ pip3 install -r "$(dirname "$0")/requirements.txt" echo "✅ Python 依赖已安装" ``` Every dependency permits unrestricted newer versions and no integrity hashes are supplied: ```text faster-whisper>=1.0.0 ffmpeg-python>=0.2.0 edge-tts>=6.1.0 requests>=2.31.0 ``` ### Technical Analysis The use of lower-bound constraints means installation can resolve any future release satisfying the minimum version. There is no lock file, exact version pin, artifact hash, or trusted repository restriction. The setup process also invokes the active `pip3` directly rather than creating an isolated virtual environment. Depending on the user's environment and permissions, packages may be installed globally, into the user site, or into another active environment. `edge-tts` and `requests` are not imported or otherwise used by the reviewed main program. Their inclusion unnecessarily expands the dependency graph and supply-chain attack surface. Python packages and their transitive dependencies may execute build or installation logic. Therefore, compromise of a package release or maintainer account could result in code execution during setup. ### Attack Path 1. A dependency maintainer account, package release, or transitive dependency is compromised. 2. The attacker publishes a malicious version that satisfies the broad `>=` constraint. 3. A user runs `setup.sh`. 4. `pip3` resolves and downloads the new malicious version. 5. Package build or installation code executes with the permissions of the user running setup. 6. The package remains installed in the active Python environment and can ex ...[truncated 759 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/douyin.py:157
Finding

Insufficient validation of MCP-provided download URLs permits requests to unintended hosts

Content
View full analysis
1000: return save_path ``` ### Technical Analysis The URL originates from output produced by the external `mcporter`/`douyin-mcp` component. Validation only checks that the URL starts with HTTP or HTTPS and contains a substring matching `v[0-9a-f]{8,}`. This does not verify: - That the hostname belongs to Douyin or an approved CDN. - That the destination is not a loopback, private, link-local, or cloud metadata address. - That HTTPS is required. - That redirect targets remain on approved hosts. - That the response has an expected content type. - That the response size is within a safe limit. The `-L` option instructs `curl` to follow redirects. Even if an initial hostname were trusted, an attacker-controlled redirect could lead to an unintended destination. The downloaded response is subsequently processed as media by FFmpeg, increasing the attack surface. ### Attack Path 1. An attacker compromises, replaces, or influences the external MCP component or its response. 2. The MCP output contains an ...[truncated 1333 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (25)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill claims 'zero paid dependencies' and presents reassuring safety language, yet the documented behavior includes optional remote/cloud services (qwen-asr, Tencent Cloud, mcporter/MCP) and possible persistent storage via memory-manager. This mismatch is dangerous because users may provide Douyin links, audio, and transcript data under false assumptions about locality, cost, and retention, increasing the risk of privacy exposure and unauthorized external data transfer.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README advertises remote/cloud ASR engines such as qwen-asr and Tencent Cloud as part of the automatic fallback chain, but it does not clearly disclose that user audio or derived text may be transmitted off-device. This creates a meaningful privacy risk because users may unknowingly send potentially sensitive voice content to third-party services during normal operation or automatic downgrade behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill documents shell execution and file writes (setup.sh, Python subprocess calls to curl, ffmpeg, uv, mcporter, and writes to ~/Desktop/...) but does not declare any explicit tool scope such as permissions or allowed-tools. This creates a transparency and consent gap: a host or user may treat the skill as lower-risk than it is, even though it can execute commands and persist files locally.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill's advertised purpose is Douyin processing, but it also persists transcript content into a separate memory-manager skill. That is a scope expansion and hidden data flow that users would not reasonably expect, especially because transcripts may contain personal or sensitive information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill silently forwards transcript excerpts into a separate memory subsystem, creating undisclosed secondary use of derived user data. Even if truncated, transcripts can contain names, credentials, or other sensitive content that should not be retained without consent.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The code stores transcribed content in plain language through a memory manager without consent, minimization, or visible retention controls. Because transcripts can contain sensitive or regulated data, persistent storage materially increases confidentiality and compliance risk if the memory store is accessed, reused, or leaked.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
93% confidence
Finding

The skill automatically sends transcript snippets to a separate memory-manager subprocess for persistent storage without explicit user consent. This creates an unexpected data-retention channel for potentially sensitive audio/video content and expands exposure beyond the stated Douyin-processing function.

Content

Scanner excerpt · scripts/douyin.py (reported line 35)May include surrounding context.

python
def memory_add(content, cat='knowledge'):
    try:
        subprocess.run(
            ['python3', MEMORY_CORE, 'add', content[:200], cat],
            capture_output=True, text=True, timeout=5,
        )

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/douyin.py (reported line 46)May include surrounding context.

python
def run_cmd(cmd, timeout=60):
    """执行命令,返回 (returncode, stdout, stderr)"""
    try:
        r = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
        return r.returncode, r.stdout, r.stderr
    except Exception as e:
        return -1, '', str(e)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description emphasizes 'zero paid dependencies' and implies local tooling, but the normal ASR path prioritizes a remote qwen-asr service and may fall back to Tencent Cloud. This mismatch can mislead users about privacy, network use, and cost exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Audio content is sent to remote/cloud ASR services in the normal processing path without a clear warning at the operation point. Since spoken content can include sensitive personal, business, or copyrighted material, undisclosed transmission to external services materially increases privacy and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The local Whisper transcription call hard-codes language='zh', which imposes a specific locale/language behavior regardless of user preference. The file does not present this as an optional or justified region-specific constraint, so it violates the language-choice policy.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Tencent Cloud ASR is included as a fallback, but that third-party data transfer is not clearly reflected in the skill's stated scope. Undisclosed cloud processing of user media can expose sensitive content and violate user expectations or organizational policy.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/douyin.py (reported line 196)May include surrounding context.

python
vid, title, dl_url = douyin_parse(url)
    if dl_url:
        log('直链下载...')
        rc = subprocess.run([
            'curl', '-sL', '-o', save_path,
            '-H', 'User-Agent: Mozilla/5.0',
            '-H', 'Referer: https://www.douyin.com/',

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/douyin.py (reported line 212)May include surrounding context.

python
"""ffmpeg 提取音频"""
    base = Path(video_path).stem
    audio_path = os.path.join(OUTPUT_DIR, f'{base}.mp3')
    rc = subprocess.run([
        'ffmpeg', '-y', '-i', video_path, '-vn',
        '-acodec', 'libmp3lame', '-ab', '128k',
        '-ar', '16000', '-ac', '1', audio_path,

Ssd 3

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

After video transcription, the skill automatically logs transcript content into memory as 'knowledge', persisting user-derived data beyond the immediate task. In the context of media processing, this is especially risky because users expect transformation of content, not secondary retention in another subsystem.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

Audio transcription results are also automatically retained in memory, extending the same privacy issue to standalone audio processing. This broadens the exposure surface because any local audio file processed by the tool may be silently copied into another persistent store.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This shell script presents its title, status messages, error guidance, and usage instructions entirely in Chinese, which imposes a specific language on all users. The file contains no option to select another language and no explanation that the skill is intended only for a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing instructions and descriptions in this file are written in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience for a documented reason. This can conflict with a language/locale policy that requires user opt-in or explicit justification for forced language use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README explicitly says results are automatically saved to the Desktop and that setup creates an output directory, but it does not clearly warn users that running the skill will write files to the local filesystem. This is a transparency and consent issue: unexpected file creation can surprise users, overwrite expectations about where data is stored, and expose sensitive transcripts on a shared machine.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The dependency is specified with a lower bound only, which allows future installs to pull any newer release, including versions with breaking changes or newly introduced vulnerabilities. In a security-sensitive automation skill that handles media processing and network access, this weakens build reproducibility and increases supply-chain risk over time.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
faster-whisper>=1.0.0
ffmpeg-python>=0.2.0
edge-tts>=6.1.0
requests>=2.31.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

Using an unpinned ffmpeg-python version permits installation of arbitrary later releases, making builds non-reproducible and increasing exposure to upstream compromise or unsafe changes. Because this skill processes untrusted media content, dependency drift in media tooling can meaningfully expand attack surface.

Content

Scanner excerpt · requirements.txt (reported line 2)May include surrounding context.

text
faster-whisper>=1.0.0
ffmpeg-python>=0.2.0
edge-tts>=6.1.0
requests>=2.31.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The edge-tts dependency is not pinned, so deployments may resolve to different versions over time with different security properties. This creates avoidable supply-chain and stability risk, especially for an automation tool that may run unattended and process externally sourced content.

Content

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

text
faster-whisper>=1.0.0
ffmpeg-python>=0.2.0
edge-tts>=6.1.0
requests>=2.31.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
98% confidence
Finding

An unpinned requests dependency is more concerning because the package has a history of published advisories, and a lower-bound constraint does not ensure a safe version is installed. Since this skill likely performs network operations, resolving to a vulnerable or unexpected requests release could expose credential leakage, TLS/verification issues, or other client-side security flaws depending on usage.

Content

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

text
faster-whisper>=1.0.0
ffmpeg-python>=0.2.0
edge-tts>=6.1.0
requests>=2.31.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
97% confidence
Finding

The manifest does not pin requests to a version, so it is impossible to verify from this file whether the installed release avoids known advisories. In a tool that likely makes outbound HTTP requests, this uncertainty is operationally dangerous because vulnerable client behavior may be introduced silently during installation or redeployment.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The code claims local Whisper processing but may trigger automatic model downloads on first use. This is not a severe exploit by itself, but it is a trust and supply-chain transparency issue because network access and large external artifacts are introduced without prominent warning.

Content

No source excerpt is available for this finding.