hugging-face-vision-trainer
Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.
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 reads training datasets from the Hugging Face Hub (cppe-5 and custom user datasets), which are third-party user-submitted repositories containing free text/annotations.
- Repository
popey/claude-code-skills
- Revision
a5a6601
- 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.