frontcli

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

• Third-party content exposure detected (high risk: 0.85). At runtime the workflow uses frontcli conv get --full --json / frontcli conv messages --json / frontcli conv comments --json to ingest conversation message bodies and comments (which can include text authored by the customer/other parties), i.e., outsider-authored free text returned by Front’s API into the agent’s LLM context.