ark-issues

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

• Third-party content exposure detected (high risk: 0.90). This skill directly searches, views, and parses GitHub issues and comments from the mckinsey/agents-at-scale-ark repository using gh search/issues and gh issue view --comments --json, which are user-generated, public GitHub contents the agent reads and interprets, exposing it to potential indirect prompt injection.