teams-setup

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

• Third-party content exposure detected (low risk: 0.10). Skill.md’s required runtime workflow ingests outsider-authored free text only from the user-supplied $ARGUMENTS prompt (Mode/Team parsing and optional PROMPT), which is then used to drive subsequent agent tasks; no other external free-text submission paths (email/chat/issue feeds/web browsing) are specified.