investigating-error-issue

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

• Third-party content exposure detected (medium risk: 0.65). The workflow ingests outsider-authored free text from PostHog issue/event records at runtime—e.g., posthog:query-error-tracking-issue and posthog:query-error-tracking-issue-events return fields like name/description and exception stack/URL that originate from external users’ reports and application code, which the agent then places into the LLM context during synthesis.