team-collaboration-standup-notes

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests outsider-authored free text from the user’s Obsidian vault and Jira ticket data at runtime (via mcp-obsidian and atlassian), which is then embedded into the LLM prompt as Context: $(cat /tmp/standup-context.json) for summarization.