image-utils

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

• Third-party content exposure detected (high risk: 0.70). The skill's code and documentation explicitly download images from arbitrary HTTP(S) URLs (see ImageUtils.load_from_url in references/code-examples/image_utils.py and the "Load from URL" examples in SKILL.md, including the Bria image_url download), which ingests untrusted public third-party content that the agent processes as part of its workflow.