code-review

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the runtime “review packet” content (e.g., PR/MR body, comments, or diff text authored by other contributors) that the skill is instructed to “start from” and normalize; this includes outsider-authored text on authenticated code hosting channels.