SKILLEMALL.ai
GitHub ↗ RU Sign in

DF MT-Paotui-For-Client

美团跑腿下单助手。支持场景：① 帮取送（A地取件送到B地，支持品类：餐饮、文件、生鲜、蛋糕、鲜花、数码、服饰、快递、五金、汽配等）② 帮买（代购商品）③ 帮取号（餐厅取号、医院挂号、其他取号）④ 帮搬装/帮扔杂物/其他帮忙（骑手到指定地址帮忙）。触发词：跑腿、下跑腿单、美团跑腿、同城配送、取号、挂号、排号、排队、帮搬、帮买、帮扔、帮忙、扔垃圾、寄文件、叫骑手、骑手帮忙、送东西、帮取、配送、帮送、买东西。

ClawHub Agent Skills author: meituan-tech v1.0.5 MIT-0 17 files · 4 scripts body ≈ 2 701 tokens Open the sourceclawhub.ai↗ analyzed 9 d ago

美团跑腿下单助手。支持场景：① 帮取送（A地取件送到B地，支持品类：餐饮、文件、生鲜、蛋糕、鲜花、数码、服饰、快递、五金、汽配等）② 帮买（代购商品）③ 帮取号（餐厅取号、医院挂号、其他取号）④…

As a process F 33/100 · No process to follow — References files that are not bundled: <path>, <AUTH_LINK>, {mobilePayUrl}

ProcedureSoftware developmenttype 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
71/100
safety, quality, tests
Safety 60%
73
Quality 40%
69
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: <path>, <AUTH_LINK>, {mobilePayUrl}
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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. 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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Dangerous commands cmd-pipe-to-shell-known-host passport-auth/reference.md:137
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
  • medium Exfiltration net-credential-use passport-auth/reference.md:179
    Credential used in a network call (verify the destination is the intended service)
    curl -H 'token: ${passport_token}' https://your-api/endpoint
  • medium Exfiltration net-credential-use passport-auth/reference.md:182
    Credential used in a network call (verify the destination is the intended service)
    curl -H "token: ${passport_token}" https://your-api/endpoint
  • medium Exfiltration net-credential-use passport-auth/reference.md:234
    Credential used in a network call (verify the destination is the intended service)
    curl -H 'X-Auth-Mode: ${passport_auth_mode}' -H 'token: ${passport_token}' https://your-api/endpoint
  • medium Exfiltration net-credential-use passport-auth/reference.md:237
    Credential used in a network call (verify the destination is the intended service)
    curl -H "X-Auth-Mode: ${passport_auth_mode}" https://your-api/endpoint
  • low Obfuscation obf-base64-blob dist/index.js:2
    Long base64-looking blob (detector / deny-list definition)
    const a0_0x2896d6=a0_0x24d4;(function(_0x427b5f,_0x598b27){const _0x1c22b3=a0_0x24d4,_0x7d3471=_0x427b5f();while(!![]){try{const _0x465516=-parseInt(_0x1c22b3(0x251))/0x1+parseInt(_0x1c22b3(0x21d))/0x
    detector
  • low Secrets in code secret-high-entropy-token dist/index.js:2
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    const a0_0x2896d6=a0_0x24d4;(function(_0x427b5f,_0x598b27){const _0x1c22b3=a0_0x24d4,_0x7d3471=_0x427b5f();while(!![]){try{const _0x465516=-parseInt(_0x1c22b3(0x251))/0x1+parseInt(_0x1c22b3(0x21d))/0x
    detector

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: <path>
  • warning missing-ref reference to a missing file: <AUTH_LINK>
  • warning missing-ref reference to a missing file: {mobilePayUrl}
  • warning missing-ref reference to a missing file: {pcPayUrl}

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: <path>, <AUTH_LINK>, {mobilePayUrl}
  • 0Tools and files. 4 referenced file(s) missing: <path>, <AUTH_LINK>, {mobilePayUrl}
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 8 mutating operations with no state check
  • 100Steps. 45 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2701 tokens

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
  • -251 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 203: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 45 items
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This skill is mostly a real Meituan errand-ordering assistant, but it bundles under-disclosed background fingerprinting and self-update behavior that should be reviewed before installation.
LLM: suspicious (high) · 20 Sept 2026