setup

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly installs and invokes a third-party plugin/skill ("claude /plugin install hookify" and Skill("hookify:writing-rules") in Phase 7 Step C), meaning it fetches and consumes external plugin-provided content/formatting that the agent then uses to generate rules, creating a clear path for indirect prompt injection via that external content.