Ark Analysis

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to clone and inspect an external GitHub repository (git@github.com:mckinsey/agents-at-scale-ark.git) and to read files (cat/grep) from that repo, which are untrusted third-party contents that the agent will interpret as part of its analysis workflow.