Back to skill
Skillv1.0.2
ClawScan security
Seedance 2.0 Prompt-Optimizer Skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 7, 2026, 7:04 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only prompt-engineering skill that is internally consistent with its stated purpose and does not request extra privileges, credentials, or installs.
- Guidance
- This skill is an instruction-only prompt-engineering guide and appears coherent with its purpose. It does not request credentials or install anything. Before using it: 1) Review any generated prompts for IP/copyright concerns (the docs explicitly warn about franchised characters but the agent could still produce problematic phrasing). 2) Do not upload private or sensitive images/audio as reference assets to any third-party generation platform. 3) Note the doc mentions platform workarounds (e.g., 'invisible watermark bypass' flags) — those are platform-level and should only be pursued through official support channels. 4) Continue to verify outputs (safety/moderation) before publishing, since a coherent skill can still produce content you may need to edit or moderate.
Review Dimensions
- Purpose & Capability
- okName/description (Seedance 2.0 prompt optimizer) match the included files and runtime instructions. All required capabilities are documentation and prompt‑construction guidance — no unrelated credentials, binaries, or platform access are requested.
- Instruction Scope
- okSKILL.md and the referenced docs direct the agent to ask targeted questions, read the included reference files, and produce structured prompts. The instructions do not ask the agent to read arbitrary system files, environment variables, or send data to external endpoints.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only. Nothing is downloaded or written to disk, which minimizes install risk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The guidance references platform behavior (e.g., watermark bypass flags) only as advisory; it does not request secrets or unrelated tokens.
- Persistence & Privilege
- okNo always:true, no special persistence or elevated privileges requested. Default autonomous invocation is allowed (normal for skills) but is not combined with other risky privileges.