cloudinary-docs

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

• Third-party content exposure detected (high risk: 0.85). The skill fetches Cloudinary documentation pages at runtime from the public web (e.g., via llms.txt and then the referenced markdown URLs), so the LLM ingests outsider-authored free text from those pages.

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 the runtime index at https://cloudinary.com/documentation/llms.txt and then retrieve documentation pages from that index to drive its answers, meaning remote content fetched at runtime directly controls the agent's prompts/responses.