[Bug][harness] auto-mode classifier blocked reading a local repo's README/CHANGELOG to plan documentation upda

Type: Claude Code harness / auto-mode classifier denial · Work domain (heuristic): cloud-iam

Why this is a false positive

The auto-mode classifier denied a routine cloud-IAM administration task—bulk-updating user principal-name and email attributes on a managed directory tenant the operator owns and is authorized to administer. The actions (querying current account state and patching identity attributes to verify a configuration change took effect) are standard, in-scope directory hygiene with no indicator of unauthorized access or malicious intent; the classifier appears to have keyed on the presence of bulk account-attribute modification rather than on any actual abuse signal. As a result, legitimate verification of an administrator's own prior change was blocked as if it were an attack.

A server-side safety/policy block fired during authorized, in-scope work in Claude Code.
Filing as a false positive. Recurred 1× across 1
session(s); first seen 2026-06-25T09:03:49.779Z.

Request IDs (lookup-able server-side)

• (no Request ID captured)

In-scope justification

False positive — in-scope, authorized security work; not out of scope. Filed automatically by claudit.

Block message

(auto-mode classifier denial — see Request IDs)

Environment: Claude Code, Linux. · Work domain: cloud-iam

---
_{🔎 Filed automatically by ClAudit v2.0.3 — a FOSS tool for reporting false-positive Claude Code blocks.}