klimkit-grill-me

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

• Third-party content exposure detected (high risk: 0.75). The workflow explicitly instructs the agent to “Search the web for current outside context” (step 5) and then to write the results into the grilling-session note that becomes LLM-readable context, which can include outsider-authored free text from public web pages.