crisis-response-planner

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime reads “the incident evidence itself (User-provided: exports, screenshots, forwarded emails)” and treats pasted mention exports/DM screenshots/forwarded journalist emails as untrusted input, which can include outsider-authored free text that the agent will ingest into the LLM context for triage/protocol generation.