ss-shadcn-svelte

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow explicitly tells the agent to fetch and read documentation from the public site https://www.shadcn-svelte.com/llms.txt (and the linked component .md pages), i.e., open/public third‑party content that the agent must interpret and act on to choose and use components, which could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to fetch https://www.shadcn-svelte.com/llms.txt at runtime to load component documentation (and linked .md pages) which would be injected into the agent's context and directly influence its instructions/behavior, so this is a runtime external dependency that controls prompts.