remotion-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions provide standard commands for installing official Remotion modules using package managers (e.g.,
npx remotion add @remotion/media). these are routine setup operations for the framework described. - [EXTERNAL_DOWNLOADS]: The skill contains examples for fetching remote media assets and Lottie animations from established domains such as
remotion.mediaandlottiefiles.com. These are documented as part of the intended functionality for video creation. - [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for ingesting untrusted external data, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Data fetching via the
fetchAPI is demonstrated incalculateMetadatafunctions (rules/calculate-metadata.md, rules/compositions.md), subtitle parsing (rules/import-srt-captions.md), and Lottie animation loading (rules/lottie.md). - Boundary markers: The provided code snippets do not include delimiters or specific instructions to the agent to ignore embedded commands within the fetched data.
- Capability inventory: The skill describes the use of network operations (
fetch), file system access viastaticFile(), and UI rendering capabilities. - Sanitization: There is no evidence of data sanitization or validation in the examples provided for processing external JSON or SRT content.
Audit Metadata