SKILLEMALL.ai
GitHub ↗ RU Sign in

BF feishu-openapi

Use this skill for Feishu/Lark OpenAPI integration work: configuring OpenClaw Feishu bot accounts, setting app credentials outside the skill, reading or writing Feishu Docx documents, creating user-owned docs, appending or editing blocks, and using Sheets, Base, Wiki, Drive, or IM APIs. Trigger when the user asks for 飞书 API, 飞书在线文档 API, OpenAPI, app id or app secret setup, document token handling, OpenClaw Feishu routing, or replacing lark-cli with direct API calls.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: luz404 v1.0.0 MIT-0 25 files body ≈ 1 513 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process F 50/100 · Will not run — References files that are not bundled: references/env.example

IntegrationWordInfrastructureWriting and documentstype 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
80/100
safety, quality, tests
Safety 60%
77
Quality 40%
85
Run on models
none yet
Process rating
F
50/100
Will not run
References files that are not bundled: references/env.example
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 2

  • high Exfiltration intent-browser-credential-store references/setup.md:43
    Accesses a browser credential / cookie store
    Do not use `lark-cli`, Feishu CLI tools, browser cookies, or browser automation as the implementation path for document operations. The OpenClaw CLI is only for OpenClaw account routing, bindings, and
Medium and low: 1
  • medium Exfiltration intent-browser-credential-store SKILL.md:15
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    All Feishu document and content operations must use OpenAPI through this skill's scripts. Do not use `lark-cli`, Feishu CLI tools, browser automation, or copied browser cookies for Docx, Sheets, Base,
    quoted

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/env.example

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: references/env.example
  • 0Tools and files. 1 referenced file(s) missing: references/env.example
  • 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
  • 40Consistency. Frontmatter name (feishu-openapi) differs from the folder (feishu-clouddoc-api)
  • 100Steps. 30 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1513 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 470: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: clean
This is a disclosed Feishu/Lark API connector that handles sensitive tokens and can edit cloud documents, but I found no hidden exfiltration or unrelated behavior.
LLM: benign (high) · 28 May 2026