earningswhispers

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

• Third-party content exposure detected (high risk: 0.95). The skill calls the outsider-owned public endpoint https://www.earningswhispers.com/api/conferencecalls?t={TICKER} at runtime and ingests the returned earnings transcript text (speakers’ text / speakers JSON) into the agent’s LLM context via the parsed prepared_remarks and qa_section fields.