pp-coffee-goat

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs the coffee-goat-pp-cli with --agent, and that CLI’s outputs (including “transcript excerpt”/creator-review snippets and other synced roaster/product data) are ingested into the agent’s LLM context; those excerpts are outsider-authored (e.g., Hoffmann/Hedrick transcripts and roaster catalog text) fetched/synced from external sources at runtime.