BD my-lark
飞书全能力技能。基于飞书官方工具服务，支持消息、群组、云文档、云盘、知识库、日历、审批、多维表格、电子表格、画板、通讯录全部模块。面向小白：安装即用，每一步都有操作指引；面向AI：每个接口均有调用示例、参数说明、权限要求和异常处理。触发词：发消息、搜索文档、查日历、查审批、建日程、拉群列表等。
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Secrets in code
secret-labelled-tokenlark_mcp.py:11Labelled token / key literal (vendor format unknown — verify it is not a live credential)APP_SECRET = "bHTI…VTZ"
-
low Secrets in code
secret-high-entropy-tokenlark_mcp.py:11High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)APP_SECRET = "bHTI…VTZ"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/bitable.md:9High-entropy token-like string (may be an id, hash or a credential)python3 /workspace/skills/lark-skill/lark_mcp.py call bita…ist '{"page_size":100}' -
low Secrets in code
secret-high-entropy-tokenreferences/bitable.md:19High-entropy token-like string (may be an id, hash or a credential)bita…ate list update delete search - 记录
-
low Secrets in code
secret-high-entropy-tokenreferences/bitable.md:20High-entropy token-like string (may be an id, hash or a credential)bita…ist create update delete - 字段
-
low Secrets in code
secret-high-entropy-tokenreferences/tools-index.md:24High-entropy token-like string (may be an id, hash or a credential)driv…ate - 添加文件协作者
-
low Secrets in code
secret-high-entropy-tokenreferences/tools-index.md:25High-entropy token-like string (may be an id, hash or a credential)driv…ist - 获取协作者列表
-
low Secrets in code
secret-high-entropy-tokenreferences/tools-index.md:53High-entropy token-like string (may be an id, hash or a credential)bita…ate - 新增记录
-
low Secrets in code
secret-high-entropy-tokenreferences/tools-index.md:54High-entropy token-like string (may be an id, hash or a credential)bita…ist - 获取记录列表
-
low Secrets in code
secret-high-entropy-tokenreferences/tools-index.md:55High-entropy token-like string (may be an id, hash or a credential)bita…ate - 更新记录
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:278High-entropy token-like string (may be an id, hash or a credential)python3 /workspace/skills/lark-skill/lark_mcp.py call bita…ist '{ -
low Secrets in code
secret-high-entropy-tokenSKILL.md:284High-entropy token-like string (may be an id, hash or a credential)python3 /workspace/skills/lark-skill/lark_mcp.py call bita…ate '{
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 43/100
- 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. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3227 tokens
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- -217 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 147: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (25 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.