remotion

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow is to run npx skills add remotion-dev/skills, which at install time will fetch third-party package/sub-skill content from the public GitHub repo; that fetched text can include outsider-authored free-form docs/code comments that the agent may ingest into its LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The SKILL explicitly instructs runtime installation (npx skills add) that fetches and installs the external package at https://github.com/remotion-dev/skills, meaning remote code and skill content that can control prompts would be fetched and executed at runtime.