daily-report

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md Step 2 explicitly instructs the agent to gather AI industry news via web search, tech media monitoring and "social media highlights" (and lists web_search / web_fetch as dependencies), so the agent ingests untrusted public/user-generated web content that directly drives report content and publishing decisions.