[Bug][harness] Listing CF Access policies blocked as recon when debugging auth bypass on user's own domain

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

Why this is a false positive

The classifier incorrectly treated a developer modifying authentication policies on their own infrastructure as an attack against a shared production target — but the entire conversation context shows active debugging of a self-owned service, including setting internal env vars, adding request logging, and purging cache, none of which an attacker would have access to do. Listing or flipping a [REDACTED] Access policy to bypass is a routine, reversible configuration change that any owner of the protected zone performs during auth troubleshooting, not reconnaissance. The block conflates "weakens security posture" with "unauthorized action," when the operator explicitly directed the change on infrastructure they control and can trivially revert.

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 2026-06-10T20:45:54.035Z.

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

Listing [REDACTED] Access policies is reconnaissance toward removing the auth gate in front of a production service, which weakens security on a shared production target.

Environment: Claude Code, Linux. · Work domain: general

---
_{🔎 Filed automatically by ClAudit v2.0.25 — a FOSS tool for reporting false-positive Claude Code blocks.}