mermaids-treasure

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

• Third-party content exposure detected (high risk: 1.00). The skill's Flowchart Construction reference (references/flowchart-construction.md) explicitly instructs the agent that "When provided a process map or Mermaid diagram, treat it as the authoritative procedure" and to execute its steps, which means untrusted/user-supplied Mermaid diagrams can be ingested and directly drive agent behavior.