codex-memory-curator

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

• Third-party content exposure detected (high risk: 0.75). High: the required workflow reads and ingests outsider-authored free text from local Codex memory files under <codex-home>/memories (and config.toml), which may contain attacker-controlled content; this text is then used to generate the review report and proposed cleanup in the agent’s LLM context.