remotion-video
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
git clone,npm install, andnpx remotion renderto prepare the environment and render videos. These are necessary for the skill's primary purpose. - [EXTERNAL_DOWNLOADS]: The skill downloads packages from the NPM registry and clones repositories from GitHub. These are well-known and established services.
- [PROMPT_INJECTION]: The skill performs deep scans of external GitHub repositories to generate video scripts. This process is vulnerable to indirect prompt injection where malicious instructions inside a scanned repository could influence agent behavior.
- Ingestion points: Automated scanning of
README.md,package.json, and source files in Phase 1. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat repo content as untrusted data.
- Capability inventory: The agent can read files, execute shell commands, and perform network operations via
git. - Sanitization: No validation or sanitization of content extracted from scanned repositories is defined.
Audit Metadata