nimbu-cloud-code

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is to fetch Nimbu documentation pages (e.g., docs.nimbu.io/... .md) at runtime; those are outsider-authored public web content that the agent can ingest as free-form markdown into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent at runtime to "Always fetch the relevant doc page" (the .md variants) from https://docs.nimbu.io (e.g. https://docs.nimbu.io/docs/cloud-code/overview.md), meaning remote markdown from docs.nimbu.io is fetched and used to control prompts/instructions.