sca-remediation

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests outsider-authored free text from Endor API responses (e.g., SCA Finding details and VersionUpgrade/UIA evidence) into the agent’s LLM context via the query-sca-findings and query-uia-evidence runtime paths, and those records are not authored by the operating user.