kata-research-phase

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

• Third-party content exposure detected (high risk: 0.90). The skill's instructions (references/phase-researcher-instructions.md and the SKILL.md execution_flow/tool_strategy) explicitly require using WebSearch and WebFetch to retrieve public websites, GitHub, Stack Overflow and other community sources and then incorporate those findings into prescriptive RESEARCH.md outputs that drive planner actions, so untrusted third‑party content is fetched, interpreted, and can change agent behavior.