make-explainer-video
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the 'explainer-studio' repository from the author's GitHub (yahyabedirhan/explainer-studio) to set up the working environment. It also downloads a voice model (approximately 330 MB) for local speech synthesis and fetches font files from Google Fonts.
- [COMMAND_EXECUTION]: The skill relies on executing various local commands via NPM and Cargo, such as
npm install,npm run setup:voice,npm run setup:skills, andcargo build. These commands are used for environment preparation, voice generation, and video rendering. - [DYNAMIC_EXECUTION]: The skill generates TypeScript and Rust source code files (e.g.,
Video.tsx,timing.rs) at runtime based on the subject matter it analyzes, then uses Remotion or FFrames to execute or compile this code into a video. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from source projects (code, documentation, pull requests) and user-provided URLs for reference videos to determine the video's narrative and visual structure.
- Ingestion points: The skill reads the 'source project' (Step 2) and downloads videos from user-supplied URLs (references/steps/reference-study.md).
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate untrusted data from the agent's core instructions.
- Capability inventory: The skill possesses extensive capabilities, including writing code to the filesystem, executing build commands, and performing network operations.
- Sanitization: The instructions do not specify any sanitization or validation logic for the content ingested from external sources.
Audit Metadata