Medeo Video
Analysis
This skill appears purpose-aligned for AI video generation and delivery, but it handles API keys, uploads user media to external services, and can use chat-platform credentials.
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Generation runs in the background — your assistant will send you the video when it's ready.
The skill intentionally starts long-running asynchronous video generation jobs and later delivers results.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Resolution priority: 1. Environment variable MEDEO_API_KEY ... 2. Skill-local config file (~/.openclaw/workspace/medeo-video/config.json)
The skill uses a Medeo API key from the environment or a local config file to call the Medeo service.
config_path = os.path.expanduser("~/.openclaw/openclaw.json") ... app_id = main_acct.get("appId", "") ... app_secret = main_acct.get("appSecret", "")The Feishu helper reads local OpenClaw Feishu app credentials to obtain a tenant token for sending generated videos.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
API flow: `prepare_for_upload` → S3 presigned PUT → `create_from_upload` → poll job → media_id
User-provided media can be uploaded through Medeo/S3-backed upload flows as part of video generation.
