fluentui

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the runtime to fetch outsider-authored public web content (FluentUI storybooks URLs) via fetch_webpage, which would ingest arbitrary free text from those pages into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to fetch external documentation at runtime (e.g., https://storybooks.fluentui.dev/react/llms.txt and https://storybooks.fluentui.dev/react/llms/components-{name}.txt) via fetch_webpage and use that content to guide its behavior/answers, meaning remote content directly controls the agent's prompts/context.