glmv-grounding

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches and processes user-supplied public http/https media (see SKILL.md and scripts/glm_grounding_cli.py -> load_media_bytes/_is_public_url which downloads --image-url/--video-url), so arbitrary untrusted third-party images/videos are ingested and can influence the model's outputs and subsequent tool actions.