flowbite-svelte

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

• Third-party content exposure detected (high risk: 0.95). At runtime the required workflow uses WebFetch to retrieve Flowbite Svelte documentation pages from https://flowbite-svelte.com/llm/.../*.md, which is public web content fetched at runtime and thus outsider-authored free text that can be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and use remote markdown docs at runtime (e.g., "https://flowbite-svelte.com/llm/components/modal.md") via WebFetch, which would directly inject external content into the agent's prompts and control its outputs.