Pod Cog
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: pod-cog Version: 1.0.12 The pod-cog skill bundle is a documentation-heavy integration for a podcast production service called CellCog. The SKILL.md file provides comprehensive instructions and prompt templates for generating scripts, show notes, and full audio episodes using an external 'cellcog' dependency. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the bundle functions as a standard wrapper for an AI-driven content generation tool.
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.
Using the skill may consume CellCog account resources and send work through the user's CellCog account.
The skill requires a CellCog API key. This is expected for a CellCog-powered production tool, but it means the agent can use the user's CellCog account credentials.
requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]
Use a scoped CellCog API key if available, monitor account usage, and avoid sharing the key outside the intended environment.
Podcast prompts, scripts, guest research details, or uploaded episode material may be sent to CellCog or the selected provider.
The skill delegates work to CellCog with an agent provider setting, indicating prompts and task content may be handled by an external agent/provider workflow.
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
Review CellCog's data handling terms and avoid submitting confidential guest, business, or unreleased content unless that external processing is acceptable.
A podcast production request may continue running after the initial command, potentially using account resources until the task completes.
The documented OpenClaw workflow creates an asynchronous agent-mode task and reports back through a notification session. This is disclosed and fits long-running podcast generation, but users should notice the background-job behavior.
**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)
Use clear task labels, monitor submitted jobs, and cancel or limit tasks if CellCog provides controls for long-running work.
The behavior ultimately depends on the CellCog SDK/package installed in the user's environment.
The skill depends on the external CellCog SDK. No malicious install behavior is shown, but the dependency is outside this instruction-only artifact.
dependencies: [cellcog]
Install the CellCog SDK from the official CellCog source and keep it updated through trusted package channels.