character-swap-h3
Warn
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The test files
assets/comfyui-h3-oneclick-swap/test_painted_area.pyandassets/comfyui-h3-oneclick-swap/test_scene.pyuseast.parseandexec(compile(...))to dynamically execute specific parts of the skill's own__init__.pycode for unit testing. While this is used for development verification, the use ofexecon compiled source code constitutes dynamic execution of local data. - [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that relies on external vision-language model outputs to generate video generation prompts, creating an attack surface for indirect prompt injection.
- Ingestion points: The nodes
H3TrackRolesandH3FillShotsprocess output from vision-language models (e.g., Qwen3-VL). - Boundary markers: The prompt templates defined in
assets/comfyui-h3-oneclick-swap/__init__.pyinclude instructions to the vision model to limit output to specific formats and subject identifiers. - Capability inventory: The skill facilitates full video generation through a ComfyUI server, involving file writes and model execution.
- Sanitization: The skill includes
neutral_shotsandneutral_wordsfunctions inassets/comfyui-h3-oneclick-swap/__init__.pythat filter the model output, removing gendered language and specific clothing descriptions to normalize the input before it is used in the final H3 generation prompt.
Audit Metadata