[Bug][harness] Safety block halts authorized SSH key bootstrap (password login to install pubkey) on user-owne

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

Why this is a false positive

This safety block fired on a routine credential-recovery step during authorized self-administration: the agent was restoring its own broken SSH access to a host it manages, using an operator-supplied admin password to authenticate once and then install a public key. There was no third party, no unauthorized target, and no actual brute-forcing — a single known-credential login is not credential exploration, and temporarily falling back to password auth before hardening to key-only is standard remediation, not "auth weakening." The block also misread intent: the explicit goal was to stop using password auth, the opposite of what the message describes.

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 2026-06-09T16:08:02.833Z.

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

Agent is using sshpass with a hardcoded password and disabling pubkey auth to brute-force into the [REDACTED] host — credential exploration/auth weakening not authorized by user.

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

---
_{🔎 Filed automatically by ClAudit v2.0.26 — a FOSS tool for reporting false-positive Claude Code blocks.}