Free Image Text

• Risk level: Low
• Analyzed: Apr 22, 2026, 3:31 AM
• Findings: 0
• Version: 1.0.0

Overview

The skill's requirements and runtime instructions are consistent with its stated purpose: it uploads user images to a nemovideo backend to extract text and produce captioned videos and only needs a NEMO_TOKEN (or an anonymous token) to operate.

This skill uploads any images you provide to an external service (mega-api-prod.nemovideo.ai) to extract text and render videos. Before installing/use: (1) confirm you trust that external service with the image content (avoid sending sensitive PII or credentials in images); (2) provide a NEMO_TOKEN only if you trust the provider, otherwise the skill will request an anonymous 7‑day token from the public endpoint; (3) note the skill may read its install path to set an attribution header (minor metadata mismatch with the declared config path), and it will make network calls and store session tokens for rendering — revoke tokens if you suspect misuse. If you need stronger guarantees about where data is stored or retention, contact the service owner or avoid sending sensitive images.