BD feishu-doc-manager
飞书文档管理技能。支持创建、读取、写入、删除文档和文档块。当用户需要操作飞书文档时使用此技能。触发条件：(1) 创建飞书文档 (2) 读取飞书文档内容 (3) 写入/追加内容到飞书文档 (4) 删除文档块 (5) 清空文档。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Exfiltration
net-credential-useSKILL.md:64Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; the skill's own vendor host)$blocksResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/docx/v1/documents/$documentId/blocks/$documentId/children" -Method Get -Headers @{ Authorization = "Bearer $token" }detectorvendor-host -
low Exfiltration
net-credential-useSKILL.md:95Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; the skill's own vendor host)$blocksResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/docx/v1/documents/$documentId/blocks/$documentId/children" -Method Get -Headers @{ Authorization = "Bearer $token" }detectorvendor-host -
low Exfiltration
net-credential-useSKILL.md:120Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; the skill's own vendor host)$blocksResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/docx/v1/documents/$documentId/blocks/$documentId/children" -Method Get -Headers @{ Authorization = "Bearer $token" }detectorvendor-host -
low Exfiltration
exfil-secret-in-urlSKILL.md:147Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)$wikiResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/wiki/v2/spaces/get_node?token=…" -Method Get -Headers @{ Authorization = "Bearer $token" }vendor-hostquoted -
low Exfiltration
net-credential-useSKILL.md:147Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)$wikiResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/wiki/v2/spaces/get_node?token=…" -Method Get -Headers @{ Authorization = "Bearer $token" }vendor-host -
low Exfiltration
net-credential-useSKILL.md:185Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; the skill's own vendor host)$blocksResp = Invoke-RestMethod -Uri "https://open.feishu.cn/open-apis/docx/v1/documents/$documentId/blocks/$documentId/children" -Method Get -Headers @{ Authorization = "Bearer $token" }detectorvendor-host
Files scanned: 3. 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 46/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (feishu-doc-manager) differs from the folder (feishu-doc-manager-pro)
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 1832 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)
- +3Description length 112: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.
External checks
ClawHub: suspicious
This Feishu document skill appears purpose-aligned, but it gives agents examples for clearing or overwriting documents without strong user-confirmation safeguards.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026