slicing-code-context

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

• Third-party content exposure detected (medium risk: 0.30). The workflow delegates to an external worker with a Trailmark slice packet containing repository source text (including comments/strings/identifiers) that an outsider could poison if they control repository contents, e.g., scripts/build_slice_packet.py reads live files into numbered_source and embeds them into the packet passed to workers.