gh

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to run gh commands that fetch GitHub data (e.g., PR/issue/workflow/run details and logs) and pass the resulting JSON/text into the agent’s context via --json/--jq/--log outputs, which can include outsider-authored free text like PR titles/bodies, issue comments, and workflow logs.