SKILLEMALL.ai
GitHub ↗ RU Sign in

BD seedance-video

使用字节跳动 Seedance 生成 AI 视频：文生视频、图生视频（首帧/首尾帧/参考图）、 异步任务查询。支持 Seedance 2.0（多模态输入、视频续生、视频编辑）等多个模型。 Use when: (1) 用户说"生成视频"/"做个视频"/"AI视频"/"text to video", (2) 用户要求根据图片生成视频/动画/"图生视频"/"image to video", (3) 用户提到 Seedance/字节视频生成, (4) 用户说"帮我做段视频"/"生成一段动画"。 NOT for: 从已有视频中抽帧/截图（用 video-frames）、 视频剪辑/转码/格式转换（用 ffmpeg 直接操作）、实拍视频处理。

ClawHub Agent Skills author: lovensky1992-wk v1.0.3 MIT-0 10 files body ≈ 983 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureMedia and videotype 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
84/100
safety, quality, tests
Safety 60%
75
Quality 40%
98
Run on models
none yet
Process rating
D
45/100
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

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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    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 references/curl-api-reference.md:74
      Credential used in a network call (verify the destination is the intended service)
      STATUS_RESULT=$(curl -s -X GET ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY")
    • medium Exfiltration net-credential-use references/curl-api-reference.md:86
      Credential used in a network call (verify the destination is the intended service)
      curl -s -X GET ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY"
    • medium Exfiltration net-credential-use references/curl-api-reference.md:89
      Credential used in a network call (verify the destination is the intended service)
      curl -s -X GET ".../tasks?page_num=1&page_size=10" -H "Authorization: Bearer $ARK_API_KEY"
    • medium Exfiltration net-credential-use references/curl-api-reference.md:92
      Credential used in a network call (verify the destination is the intended service)
      curl -s -X DELETE ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY"
    • medium Dangerous commands cmd-eval-dynamic seedance.py:230
      Dynamic code execution from decoded/untrusted input
      os.system(f'open "{filepath}"')

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 45/100

    • 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
    • 40Consistency. Frontmatter name (seedance-video) differs from the folder (seedance-video-gen)
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 100Steps. 14 steps
    • 100Execution cost. Instruction body is 983 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

    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +4Description says when NOT to use the skill
    • +3Description length 319: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 98.

    External checks

    ClawHub: clean
    This appears to be a coherent Seedance video-generation helper, but users should know it sends prompts and images to Volcengine Ark and may auto-open downloaded videos on macOS.
    LLM: benign (medium) · VirusTotal: · 29 May 2026