fix-findings

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text via the MCP tool outputs findings_list() / findings_get() / preview_fix() / create_fix(), where Agents returns finding/task title, summary, action_description, and especially code snippets that originate from Infracost’s Agents service (i.e., not authored by the operating user) and are then placed into the agent’s LLM context for decision-making.