media-gen
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a standalone Python client (
scripts/media_gen_client.py) that the agent executes to handle model routing and API communication. - [EXTERNAL_DOWNLOADS]: The skill connects to AIsa API endpoints at
api.aisa.oneto generate media and downloads resulting images and videos to the local filesystem. These network operations target vendor-owned infrastructure and support core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and external image URLs, establishing a standard surface for indirect prompt injection.
- Ingestion points: User input provided to the
--promptand--img-urlarguments in thescripts/media_gen_client.pyscript. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when passing input to the API.
- Capability inventory: The skill has the ability to perform network requests and write binary files to the local system.
- Sanitization: No input sanitization or filtering is performed on the prompt or URL content before transmission.
Audit Metadata