Meta Video Ad Analyzer

Extract and analyze content from video ads using Gemini Vision AI. Supports frame extraction, OCR text detection, audio transcription, and AI-powered scene analysis. Use when analyzing video creative content, extracting text overlays, or generating scene-by-scene descriptions.

This skill appears to do what it says (extract frames, OCR, transcribe audio, call Gemini/Vertex), but metadata omitted the required Google credentials. Before installing or running: 1) Confirm you are comfortable providing a Google service-account JSON and only grant the least-privilege roles (Vertex AI / Speech-to-Text / Cloud Storage if needed) — DO NOT use a project-owner or broad admin key. 2) Inspect the remaining functions (analyze_frames_batch, analyze_video_natively, reconciliation) for any hard-coded or external endpoints to ensure frames or transcripts are only sent to Google/Vertex and not to unknown servers. 3) Consider running the code in a sandbox with a restricted service account and test with non-sensitive videos. 4) If the registry claims 'no env vars', ask the publisher to update metadata to declare GOOGLE_APPLICATION_CREDENTIALS (and any other required env vars) before trusting the skill. If you cannot verify these details, treat it as untrusted and avoid supplying high-privilege credentials.

Type: OpenClaw Skill Name: meta-video-ad-analyzer Version: 1.0.0 The skill bundle is classified as benign. It uses `subprocess.run` for `ffmpeg` and `ffprobe` for video processing and accesses `GOOGLE_APPLICATION_CREDENTIALS` for Google Cloud API authentication, which are high-risk capabilities but are necessary and used appropriately for the stated purpose of video analysis. The prompt files (`prompts/*.md`) contain strict instructions for the LLM to control its output format, which is a defensive measure against unstructured responses, not an attempt at prompt injection against the OpenClaw agent.