veomni-new-model
Use this skill when adding support for a new model to VeOmni. Owns the lifecycle around the modeling itself: analyzing the HuggingFace model, choosing the category, the training config, trainer and data-pipeline integration, tests and docs. The modeling patch itself is delegated to /veomni-patchgen-model. Trigger: 'add model', 'support new model', 'integrate a model', 'new model support'.
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow instructs the agent to read HuggingFace model files (`config.json`, `modeling_*.py`), which are fetched from HuggingFace repositories and represent outsider-authored free text ingestion without prior selection of a specific trusted item.
- Repository
ByteDance-Seed/VeOmni
- Revision
eba362d
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.