SKILLEMALL.ai
RU Sign in

BF cue-buddy

Use when the user wants to author / validate / debug / test / tune / pin-as-frequent a Cue 搭子(buddy) research template for a recurring scenario (corporate-credit pre-diligence, compliance snapshot, earnings review, private-fund DD, etc.) via natural conversation. 让业务专家在自己的 AI agent 里无需写代码，用自然语言起草、校验、调试、测试并提交 Cue 搭子模板：跨检查能力目录核验每个证据源、跑测试验证模板质量、按需调优，最终提交到 cuecue.cn 个人模板库供 cue-research 复用。Triggers: 创建搭子 / 做一个 X 搭子 / 调试模板 / 测试我的搭子 / 提交模板 / 设为常用 / design a buddy for X / mark template as frequent. Public-data tool surface only — refuse for private-data scenarios (real AML / medical diagnosis / internal accounting).

ClawHub Agent Skills author: wangxiaoxu v1.0.1 MIT-0 22 files body ≈ 3 961 tokens Open the sourceclawhub.ai↗ analyzed 22 h ago

Use when the user wants to author / validate / debug / test / tune / pin-as-frequent a Cue 搭子(buddy) research template for a recurring scenario…

As a process F 39/100 · Will not run — References files that are not bundled: ../cue-research, ../community-invite.md

AnalyzerGitHubAI 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
B
75/100
safety, quality, tests
Safety 60%
74
Quality 40%
77
Run on models
none yet
Process rating
F
39/100
Will not run
References files that are not bundled: ../cue-research, ../community-invite.md
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. 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 · 10

✓ No critical or high findings

Medium and low: 10
  • medium Exfiltration net-redirectable-api-key scripts/cue_api.py:165
    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/test_capabilities_client.py:114
    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/test_corporate_credit_coverage.py:139
    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/test_cue_api_client_contract.py:225
    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 scripts/test_capabilities_client.py:208
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…mes(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/test_skill_regression.py:34
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…ame(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/test_skill_regression.py:55
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…les(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/test_skill_regression.py:112
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…ion(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/test_skill_regression.py:175
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…int(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/test_skill_regression.py:229
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Case…ies(unittest.TestCase):
    fixture

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../cue-research
  • warning missing-ref reference to a missing file: ../community-invite.md

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: ../cue-research, ../community-invite.md
  • 0Tools and files. 2 referenced file(s) missing: ../cue-research, ../community-invite.md
  • 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
  • 30Running it twice. 19 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 56 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3961 tokens
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (18 tags): a typed call is more reliable

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
  • -37 of 12 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 615: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 56 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious
The skill mostly matches its Cue template-authoring purpose, but it includes a built-in self-update path and automatic update check that can change or phone home about the installed skill outside the core workflow.
LLM: suspicious (high) · VirusTotal: · 11 Aug 2026