remotion-best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by instructing the agent to fetch and process untrusted data from external URLs.
- Ingestion points: Data is retrieved using fetch() and WebFetch in files such as rules/calculate-metadata.md, rules/import-srt-captions.md, rules/lottie.md, and rules/compositions.md.
- Boundary markers: The provided code examples do not include delimiters or specific instructions to treat external data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill utilizes network access to fetch JSON data, subtitles, and animation assets from remote locations.
- Sanitization: The examples do not demonstrate validation or sanitization of the fetched external content before it is used in the rendering process.
- [PROMPT_INJECTION]: Metadata inconsistency detected in the SKILL.md frontmatter. The author is declared as 'remotion-dev', which differs from the platform-provided author identity 'AndrewHaward2310'. This discrepancy could mislead users regarding the skill's official origin.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of various Node.js packages within the Remotion ecosystem and the mediabunny library to handle media metadata and processing.
Audit Metadata