Best practices for Remotion - Video creation in React
56%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/remotion-best-practices/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow only reads first-party Remotion docs and the user's own files, but the optional sound-effect guidance tells the agent to search the internet for more sound effects, which is arbitrary outsider-published content it must actively fetch.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The Lottie example fetches animation JSON from a runtime URL and renders it as the visual output, and that JSON is attributable only to an unidentified LottieFiles creator rather than a first-party publisher, so it is a common/reputable unofficial dependency (medium); the other URLs are either static docs, placeholders, media assets, or official Remotion/Mapbox/ElevenLabs sources.
calesthio/OpenMontage
fecb9a1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.