Story 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

A CellCog API key may allow the skill to use the user's CellCog account or quota when creating chats.

Why it was flagged

The skill requires a CellCog API key, which is expected for this provider integration, but the user should recognize that installing and using it involves delegated account access.

Skill content
Required env vars: CELLCOG_API_KEY ... Primary credential: none
Recommendation

Use a dedicated or least-privileged CellCog key if available, keep it secret, and revoke it if no longer needed.

What this means

Story ideas, drafts, or other prompt content may be transmitted to CellCog for processing.

Why it was flagged

The documented workflow sends the user's writing prompt to CellCog and can use agent-style chat modes. This is central to the skill's purpose, but it means user content leaves the local conversation boundary.

Skill content
result = client.create_chat( prompt="[your task prompt]", notify_session_key="agent:main:main", task_label="my-task", chat_mode="agent" )
Recommendation

Avoid sending highly sensitive unpublished material unless you are comfortable with CellCog's handling of that content.

What this means

The actual behavior depends partly on the CellCog SDK or skill that the agent uses at runtime.

Why it was flagged

The skill depends on the separate CellCog package/skill. This is purpose-aligned, but the dependency itself is not included in this instruction-only artifact.

Skill content
dependencies: [cellcog]
Recommendation

Install CellCog from a trusted source and review its own permissions and documentation before relying on this skill.