{"version":"2.1.186","anchor":"security-classifier-scope-refined","canonical_anchor":"security-classifier-scope-refined","heading":"Security Classifier Scope Refined","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.186\/e\/security-classifier-scope-refined","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.186","markdown":"### Security Classifier Scope Refined\n\nThe automode security classifier's scope description was sharpened to clarify exactly what it does and does not block.\n\n**Details**\n\n- Scope now explicitly reads: \"prevents **destructive, hard-to-undo, or security-relevant actions** only.\"\n- Explicitly out of scope: \"fabricating or misreporting results; posting updates the user didn't ask for; poor code, wrong answers, looping, wasted tokens.\" These are for the user to correct, not the classifier.\n- A new `EDIT REMOVALS` annotation is now included in classifier context: removals in `Edit` calls are noted with `removes` \/ `adds` fields. Deletions are now weighted as seriously as additions. If `removesTruncated: true`, the full removal should be treated as significant.\n- NotebookEdit calls are annotated with `mode` and `cell_id`, and deleted cell content is treated as unverifiable per the high-severity rules.\n\n**Evidence**\n\nRevised classifier prompt (search for `\"EDIT REMOVALS: Edit calls show both \\`removes\\`\"` and `\"destructive, hard-to-undo, or security-relevant actions\"`)"}