SKILLEMALL.ai
GitHub ↗ RU Sign in

CF web-collection

通过云端连接器优先执行浏览器插件数据采集，也可回退到本地连接器；适用于抖音、TikTok、小红书、Amazon、Bilibili 的采集任务，以及 web-collection 首次上手、配置、付费使用说明和 QA 排障。

ClawHub Agent Skills author: yiming1001 v1.2.9 MIT-0 13 files · 7 scripts body ≈ 8 235 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 53/100 · Will not run — References files that are not bundled: assets/bitable-step-00-personal-center.png, assets/bitable-step-01-template-copy.png, assets/bitable-step-02-auth-code.png

ProcedureInfrastructureMarketingtype 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
C
68/100
safety, quality, tests
Safety 60%
79
Quality 40%
52
Run on models
none yet
Process rating
F
53/100
Will not run
References files that are not bundled: assets/bitable-step-00-personal-center.png, assets/bitable-step-01-template-copy.png, assets/bitable-step-02-auth-code.png
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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Exfiltration net-credential-use scripts/ensure_connector_auth.sh:128
    Credential used in a network call (verify the destination is the intended service)
    curl -fsS --max-time 3 -H "x-connector-admin-token: $token" "${BRIDGE_URL}${path}"
  • medium Exfiltration net-redirectable-api-key scripts/preflight_check.sh:7
    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/run.sh:33
    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-credential-use SKILL.md:460
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "x-connector-admin-token: $TOKEN" "http://127.0.0.1:19820/api/status"
  • low Dangerous commands cmd-background-process scripts/collect_and_export_loop.sh:165
    Starts a background / autostarted process
    nohup bash -lc "$BRIDGE_CMD" >"$BRIDGE_LOG" 2>&1 &

Files scanned: 13. 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 ≈ 8235 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/bitable-step-00-personal-center.png
  • warning missing-ref reference to a missing file: assets/bitable-step-01-template-copy.png
  • warning missing-ref reference to a missing file: assets/bitable-step-02-auth-code.png
  • warning missing-ref reference to a missing file: assets/bitable-step-03-config-save.png
  • warning missing-ref reference to a missing file: assets/connector-step-01-status-token.png
  • warning missing-ref reference to a missing file: assets/install-extension-connector.gif
  • warning missing-ref reference to a missing file: assets/install-extension-connector.png
  • warning missing-ref reference to a missing file: assets/configure-bitable.gif
  • warning missing-ref reference to a missing file: assets/configure-bitable.png
  • warning missing-ref reference to a missing file: assets/verify-connector.gif
  • warning missing-ref reference to a missing file: assets/verify-connector.png
  • warning missing-ref reference to a missing file: assets/copy-device-token.gif
  • warning missing-ref reference to a missing file: assets/copy-device-token.png
  • warning missing-ref reference to a missing file: assets/view-results.gif
  • warning missing-ref reference to a missing file: assets/view-results.png
  • warning missing-ref reference to a missing file: assets/install-extension-connector.*

Process rating: all ten parameters 53/100

Will not run. References files that are not bundled: assets/bitable-step-00-personal-center.png, assets/bitable-step-01-template-copy.png, assets/bitable-step-02-auth-code.png
  • 0Tools and files. 16 referenced file(s) missing: assets/bitable-step-00-personal-center.png, assets/bitable-step-01-template-copy.png, assets/bitable-step-02-auth-code.png
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8235 tokens: crowds the task out of the window
  • 100Steps. 298 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 26 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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)
  • +3Description length 111: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 298 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.

External checks

ClawHub: suspicious
This skill appears purpose-built for browser-based data collection, but it uses stored connector credentials and raw shell-based helper paths with broad authority that users should review before installing.
LLM: suspicious (medium) · VirusTotal: · 28 Jun 2026