securing-s3-buckets

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests outsider-authored free text via aws s3api get-bucket-policy --output text (and other get-* audit reads), where the bucket policy JSON is authored by the bucket owner/other parties and is then merged/embedded into the agent’s LLM context for subsequent processing.