byted-las-vlm-video

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md and scripts/skill.py) accepts arbitrary public video URLs via the --video-url / video_url field and sends them to the remote operator endpoint (https://operator.las..volces.com/api/v1/process) for model analysis, so untrusted, user-provided video content can influence model outputs and therefore enable indirect prompt injection.