Comi Cog
PassAudited by ClawScan on May 1, 2026.
Overview
Comi Cog appears purpose-aligned for AI comic creation, but users should understand it uses a CellCog API key and sends prompts to CellCog agent workflows.
This skill looks safe to use for its stated purpose if you trust CellCog. Before installing, make sure you are comfortable providing a CellCog API key and sending your comic prompts, character descriptions, and related creative material to the CellCog service.
Findings (4)
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.
Use of this skill may consume CellCog account quota or billing tied to the API key.
The skill requires a CellCog API key, which is sensitive account authority, but this is disclosed and expected for a CellCog-powered creative generation service.
requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]
Use a revocable CellCog API key, monitor usage, and avoid sharing the key outside the intended environment.
Prompts, character descriptions, story ideas, and possibly creative assets may be sent to CellCog for processing.
The skill routes the user's prompt into a CellCog agent/provider workflow. This is core to the skill, but the artifact does not define provider-side data retention or sharing boundaries.
from cellcog import CellCogClient\nclient = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")\nresult = client.create_chat(\n prompt="[your task prompt]",\n task_label="my-task",\n chat_mode="agent",\n)
Do not include confidential or third-party-sensitive content unless you are comfortable sending it to CellCog and have reviewed the provider's terms and privacy practices.
A task may keep running remotely until CellCog completes it, rather than stopping immediately when the local agent call returns.
The OpenClaw workflow is explicitly asynchronous and agent-mode. This is disclosed and aligned with remote comic generation, but it means work can continue after the initial invocation.
**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n prompt="[your task prompt]",\n notify_session_key="agent:main:main",\n task_label="my-task",\n chat_mode="agent",\n)\n```
Launch only user-approved tasks and keep task labels/session notifications clear so generated work can be tracked.
Trust in this skill also depends on the trustworthiness of the CellCog dependency and service.
The skill depends on the separate CellCog SDK/skill reference. That dependency is purpose-aligned, but it is outside this artifact's instruction-only file.
dependencies: [cellcog]\n...\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference
Install or enable the CellCog dependency only from a trusted source and review its permissions separately if available.