[Bug][harness] Credential lookup in user-specified config path blocked as unauthorized exploration

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

Why this is a false positive

The user explicitly requested credential verification via a dedicated skill and provided the exact config file path in the same message, making token-pattern searches in that directory the literal task — not unsolicited exploration. The block misclassifies reading a user-specified credential file (to fulfill a direct "verify credentials" request) as out-of-scope discovery, when the file location and purpose were both disclosed by the user before the search occurred. This is a false positive because the safety heuristic cannot distinguish between an unprompted credential sweep and a targeted read of a file the user named and authorized.

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 2026-06-10T16:41:23.930Z.

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

Searching shell history and config directories for [REDACTED] API tokens (cfat_/cfut_ patterns) is credential exploration beyond the user's request to verify [REDACTED] credentials.

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

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