[Bug][aup] False safety block stops drafting a config skill that auto-recovers from spurious policy refusals

Type: AUP / Usage-Policy block (false positive) · Work domain (heuristic): general

Why this is a false positive

A legitimate, authorized infrastructure-administration task—querying a self-hosted management API on the operator's own systems and routing the output through a local script—was halted with a Usage Policy refusal, despite containing no harmful instruction, target, or payload. The triggering content was ordinary read-only operational tooling (a status query parsed by a local interpreter) on assets the operator owns and is authorized to manage, which falls squarely within permitted system-administration use. The block appears to be a pattern-level false positive driven by surface features (an API call piped into a script) rather than any actual policy-violating intent or capability, and it interrupts in-scope work with no recoverable path short of clearing the session.

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 2026-06-08T06:32:56.778Z.

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

API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task. If you are seeing this refusal repeatedly, try running /model claude-sonnet-4-20250514 to switch models.

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

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