octave-win-loss-report

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests outsider-authored free text via Octave conversation intelligence—e.g., list_findings pulls CALL_EXTERNAL_OBJECTIONS / competitor mentions / feature requests from recorded calls or extracted transcripts, which are not authored by the operating user and are then used to render evidence quote blocks in the generated HTML.