meeting-brief

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md and scripts/run_daily.sh) and the research prompt generator (scripts/research_person.js) explicitly instruct the agent to perform web_search and GitHub lookups of public LinkedIn/company pages and news (untrusted, user-generated content) and then feed that research into AI brief generation (scripts/generate_brief.js) whose output is used to send emails/Slack messages, so third‑party content is read and can directly change agent actions.