streak

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

• Third-party content exposure detected (high risk: 0.80). The skill's Flow 2 (Check-in) includes an explicit "Research (Optional
• Building/Learning types)" step in references/flows-detailed.md and references/types.md that tells the agent to "search for updates" and "summarize 2-3 findings" (i.e., fetch and interpret public web/news/tooling content) which the agent then uses to drive ideation and session preparation, exposing it to untrusted third‑party content that could influence actions.