SKILLEMALL.ai
GitHub ↗ RU Sign in

FD vectcut-skill

VectCut 全能剪辑聚合技能。用于剪口播、混剪、电商广告等场景，统一编排流光剪辑能力（字幕、音频、特效、画中画、抠像、AI补镜、AI配音、预设、平台视频抓取、渲染导出），也支持把既有视频制作流程整理为飞书多维表格自动化工作流。当用户提出“做成片/自动剪辑/口播包装/广告剪辑/抓平台视频后再剪”，或想把视频制作流程固化为飞书多维表格 AI Agent 工作流时，必须优先使用本技能。

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: sun-guannan v1.5.11 MIT-0 69 files body ≈ 1 240 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsInfrastructuretype 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
F
33/100
safety, quality, tests
Safety 60%
10
Quality 40%
67
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. 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 · 3

  • critical Exfiltration exfil-send-secrets-to-url rules/sts-upload.md:40
    Instruction to send secrets/history to an external endpoint
    2. **Upload to OSS** — Signs a PUT request using HMAC-SHA1 over the STS credentials and uploads the file directly to `https://{bucket_name}.{oss_endpoint}/{object_key}`.
Medium and low: 2
  • low Obfuscation obf-hex-escape-chain references/bgms.json:13
    Escaped/char-code string obfuscation (quoted — discussed, not commanded)
    "https://player.install-ai-guider.top/koubo/bgm/%E5%BF%99%E7%A2%8C%E7%9A%84%E7%94%9F%E6%B4%BB%E4%BA%BA%E5%B1%B1%E4%BA%BA%E6%B5%B7.MP3",
    quoted
  • low Secrets in code secret-high-entropy-token rules/query-draft.md:64
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "91E0…A2B",
    quoted

Files scanned: 69. 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")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "dependency"

Process rating: all ten parameters 41/100

  • 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
  • 40Consistency. Frontmatter name (vectcut-skill) differs from the folder (vectcut)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 103 steps
  • 100Execution cost. Instruction body is 1240 tokens
  • 100Running it twice. No mutating operations

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
  • +4No input/output examples
  • -330 of 31 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 193: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 103 items
  • +4Reference files are cited in the instructions (31 of 32)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: suspicious
This is a powerful cloud video-editing skill, but it includes unsafe credential handling and broad automatic media-processing behavior that users should review before installing.
LLM: suspicious (high) · 27 May 2026