Deny-by-default authority preset for agents reviewing untrusted content
What this changes for operators
- PR #7530 (in v2026.609.0) adds a low_trust_review authority preset, source-trust tagging, route containment, and quarantine so an agent reviewing a hostile PR/comment/attachment gets narrower authority and its output cannot flow into higher-trust context. Enforced authority for the untrusted-input boundary, not a dashboard label.
Primary sources
Signal metadata
Source findings
- 2026-06-05-paperclip-low-trust-review-containment 2026-06-05-paperclip-low-trust-review-containment
Run: 2026-06-16-weekly-digest-2026-06-04_2026-06-16-frontier-v0
Schema: bitter.frontier_signals.v0 / ID: 2026-06-05-paperclip-low-trust-review-containment
Research evidence and publication history are open in the repository.