agent-right-brain
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
rawgenaiCLI tool from a third-party Homebrew tap (WHQ25/tap/rawgenai), which is a vendor-owned resource for the skill's author. - [COMMAND_EXECUTION]: The skill extensively uses the
rawgenaicommand to interact with various GenAI providers for tasks like text-to-speech, image generation, and video processing. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various sources that are interpolated into prompts for external AI services.
- Ingestion points: Processes user-provided text prompts, local audio files for transcription (
stt), and JSON-formatted scripts for dialogue generation. - Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions to separate user-provided content from agent instructions when calling the CLI.
- Capability inventory: The skill can execute shell commands (
rawgenai) and perform file system operations (read/write access for media files). - Sanitization: No explicit sanitization or validation of the input data is described before it is passed to the underlying AI models.
Audit Metadata