ralph-docs

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch and read the public documentation map at https://mikeyobrien.github.io/ralph-orchestrator/llms.txt and the linked .md pages and to base answers and follow-up actions on those pages, which is reading untrusted third‑party web content that can influence tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches and relies at runtime on https://mikeyobrien.github.io/ralph-orchestrator/llms.txt (and the linked .md pages it instructs agents to fetch) to determine what the agent should say and do, so external content directly controls prompts and is a required dependency.