create-teammate

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly auto-collects and fetches public/user-generated content (e.g., tools/slack_collector.py and github_collector.py, SKILL.md Step 2 Option E with web_fetch/curl, and INSTALL.md Slack/GitHub setup) and instructs the agent to read and analyze that third-party material as core source material to generate persona/work rules that drive subsequent tool use and behavior, creating a clear vector for indirect prompt injection.