Expand description
Fencing for text that other people wrote.
Issue descriptions, comments and Wiki pages are the one part of a response
that an outsider fully controls, which makes them the injection surface an
agent actually faces (docs/adr/0001-security-model.md). We do not try to
sanitise that text — rewriting someone’s issue would be worse than useless.
We label its boundaries so the reader, human or model, can tell content from
instruction.
Enums§
- Author
- Who wrote a fenced block.