remotion-render
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshcommand-line tool for authentication and to trigger video rendering jobs on the inference.sh cloud infrastructure. - [EXTERNAL_DOWNLOADS]: Instructions are provided to install the
infshCLI vianpxand add related skills from the vendor's repository (inference-sh/skills). These are recognized as legitimate vendor resources. - [DATA_EXFILTRATION]: User-provided or agent-generated React code is transmitted to the
inference.shservice. This is the primary function of the skill and occurs within the vendor's ecosystem. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it accepts React TSX code and properties (ingestion points:
codeandpropsinSKILL.md) which are then processed by theinfshrendering capability. While no explicit boundary markers or sanitization logic are defined in the skill instructions to mitigate malicious code injection from untrusted inputs, this is consistent with the skill's purpose as a code-to-video renderer.
Audit Metadata