Seedance Cog

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The skill can use your CellCog API credentials and may consume your account quota or billable usage when generating videos.

Why it was flagged

The skill requires a CellCog API key, which is expected for calling the CellCog video service but is still account-level credential access.

Skill content
requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]
Recommendation

Use a dedicated or revocable CellCog API key where possible, monitor usage, and avoid sharing the key with unrelated skills.

What this means

Installing or using this skill also depends on trusting the separately installed CellCog package or skill.

Why it was flagged

The skill relies on an external CellCog package/skill that is not included in the provided artifact set; this is consistent with the purpose but means trust extends to that dependency.

Skill content
dependencies: [cellcog] ... Manual setup: `pip install -U cellcog`
Recommendation

Install CellCog only from the expected official source and review its permissions and credential handling before use.

What this means

Prompts, scripts, or source material you provide may be sent to CellCog and downstream generation models to produce the video.

Why it was flagged

The skill discloses that prompts are processed through CellCog and multiple model components; this is central to the video-generation purpose but involves external provider/model flows.

Skill content
CellCog orchestrates it with scripting, voice synthesis, lipsync, scoring, and editing ... **6-7 foundation models** work together in a single request
Recommendation

Do not include confidential, regulated, or private material in prompts unless you intend it to be processed by CellCog and have reviewed the provider's data practices.