Video Content Analyzer (Fixed)

Analyze videos by extracting frames every 10s, searching web references, storing metadata in Supabase, and generating Feishu Wiki reports.

This skill contains working code that requires several secrets (Supabase service role key, Google API key, Feishu app secret) but the registry metadata incorrectly lists no required env vars — treat that as a red flag. Most important: do NOT provide SUPABASE_SERVICE_ROLE_KEY unless you fully trust the source; that key bypasses row-level security and can read/modify your entire database. Prefer running the code in an isolated environment and: 1) review the source yourself (you have it) before providing secrets; 2) use a least-privilege Supabase key (a restricted service account or per-user token) instead of service_role where possible; 3) create and test with throwaway/test Supabase and Feishu projects to confirm behavior; 4) verify the Feishu app and Google CSE are yours and have appropriate scopes/quotas; 5) be cautious about the AGENTS.md/BOOTSTRAP.md guidance — those files instruct an agent to read and persist local memory files and to commit/push changes, which could expose local data if followed. If you can't audit the code or provide restricted credentials, avoid installing or run it only in an isolated container/VM.

Type: OpenClaw Skill Name: video-content-analyzer-fixed Version: 1.0.1 The skill bundle provides a legitimate video analysis workflow that integrates ffmpeg for frame extraction, Google Custom Search for content referencing, Supabase for metadata storage, and Feishu Wiki for reporting. The code in src/main.py and its modules is well-structured, follows the stated purpose, and includes appropriate error handling. While the DatabaseClient (src/modules/database_client.py) utilizes a high-privilege Supabase Service Role Key to manage user profiles and assets, this behavior is explicitly documented in the SKILL.md and aligned with the workflow's requirements. The included framework files (AGENTS.md, SOUL.md) contain proactive security instructions for the agent, such as explicit prohibitions against data exfiltration and unauthorized external actions.