SKILLEMALL.ai
GitHub ↗ RU Sign in

DF douyin-upload-mcp-skill

抖音自动投放与登录守卫。用于抖音创作者平台自动发布视频/图文、检测登录失效、生成二维码、处理短信/机器人/安全验证、同步数据生成分析、根据数据生成下一条视频方案、自动回复评论/私信、数字人形象定制/训练、一键成片、截图并通过飞书提醒客户。遇到抖音发布、投放、二维码登录、客户扫码、登录过期、发布前检查、字段化短视频发布任务、数据分析、生成下一条视频内容、训练数字人、形象定制时必须使用。飞书用户消息必须实际调用 douyin__douyin_feishu_route_text，不要只解释计划。

Not recommendedlow grade D
ClawHub Agent Skills author: Chen Yuheng v0.1.8 MIT-0 80 files · 1 script body ≈ 5 304 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 36/100 · Will not run — References files that are not bundled: references/automation-workflow-table.tsv, references/mentor-function-table.tsv

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
59/100
safety, quality, tests
Safety 60%
62
Quality 40%
54
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: references/automation-workflow-table.tsv, references/mentor-function-table.tsv
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 18

✓ No critical or high findings

Medium and low: 18
  • medium Exfiltration net-redirectable-api-key scripts/digital-human-training.js:206
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/douyin-auto-reply.js:432
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/douyin-data-report-from-bitable.js:175
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/douyin-next-video-plan-from-bitable.js:344
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/persona-flow.js:382
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Secrets in code secret-high-entropy-token package-lock.json:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…loF+i+flI8…PC6+pdqy…YWO+E2Nw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:129
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…bKX+KS9G…yMA/NhKJ…RGz/Q==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:139
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…GLi+2W/6ao+6Y7gu/RCwR…Kng==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:249
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…Wwy+ghLE…vfU/YnxW…fdg==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:283
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…DYr+NSUK…Itc/irNR…37y+AMujNyNtG+1Rggw==",
    quoted
  • low Exfiltration read-dotenv README.md:61
    Reads a .env file
    cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local
  • low Exfiltration read-dotenv README.md:79
    Reads a .env file
    cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local
  • low Exfiltration read-dotenv README.md:170
    Reads a .env file
    cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local
  • low Exfiltration read-dotenv references/customer-install-guide.md:69
    Reads a .env file
    cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local
  • low Exfiltration read-dotenv references/mentor-clawhub-deployment-plan.md:81
    Reads a .env file
    cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local
  • low Exfiltration read-dotenv scripts/export-skill-package.js:179
    Reads a .env file (security demo / example; quoted — discussed, not commanded)
    includeEnv ? 'Review .env/.env.local on the target machine and rotate keys if needed' : 'cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local, then fill target mach
    demoquoted
  • low Exfiltration read-dotenv SKILL.md:102
    Reads a .env file (quoted — discussed, not commanded)
    4. 安装后运行 `npm install`/`npm ci`、`cp references/skill-local-config.md .env.local 2>/dev/null || cp .env.example .env.local`、`node scripts/bootstrap-openclaw.js --apply`；填写 `.env.local` 和 `~/自动营销/xiaoic
    quoted
  • low Dangerous commands cmd-privilege src/daemon/engine.js:184
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    ? ['--no-sandbox', '--disable-setuid-sandbox']
    code literal

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5304 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/automation-workflow-table.tsv
  • warning missing-ref reference to a missing file: references/mentor-function-table.tsv

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: references/automation-workflow-table.tsv, references/mentor-function-table.tsv
  • 0Tools and files. 2 referenced file(s) missing: references/automation-workflow-table.tsv, references/mentor-function-table.tsv
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 13 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 5304 tokens
  • 100Steps. 127 steps
  • 100Consistency. Name and required fields are in place
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -330 of 53 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 247: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 127 items
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (11 of 13)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: suspicious
The skill broadly matches its Douyin automation purpose, but it grants persistent account-control and messaging authority with several under-scoped behaviors users should review first.
LLM: suspicious (high) · 28 May 2026