b20-console

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

• Third-party content exposure detected (high risk: 0.75). The required workflow calls a public hosted API (https://b20.charon.codes/api/inspect) and ingests its JSON response (including token metadata, risk flags, and optional source/provenance fields) into the agent via the helper script’s sanitized plain-text output, which is outsider-authored free-form content from a third party.