workiq-preview

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored free text from the user’s natural-language request via the agentic ask tool (SKILL.md grounding rules indicate answers are synthesized from tool results based on that input), and ask can orchestrate multi-step reads across M365 data.