discover-brand

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

• Third-party content exposure detected (high risk: 0.85). The required workflow delegates to a “discover-brand agent” that performs broad discovery and deep fetch across connected third-party platforms (e.g., Slack/Gong/Granola transcripts and document contents), so outsider-authored free text from those systems is likely retrieved and then passed back into the agent/LLM context via the Task tool.