remotion-video-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted external data, specifically motion design specifications (
VIDEO_SPEC.md) and Remotion source code files. This ingestion creates a potential attack surface where an attacker could embed malicious instructions within these files to influence the agent's review logic or output. - Ingestion points: The agent is instructed to read
VIDEO_SPEC.mdand various.tsx/.tsfiles from the project directory. - Boundary markers: There are no defined delimiters or instructions to the model to ignore or escape embedded prompts within the analyzed data.
- Capability inventory: The skill is designed for static analysis and reporting; it does not possess tools for automated command execution, file modification, or network exfiltration that could be easily abused by an injection.
- Sanitization: No sanitization or validation of the input file content is implemented or described.
Audit Metadata