[Bug][aup] Safety block halts legitimate phishing/BEC email investigation and incident report for admin's own (req_011CcPH3vmFMPzj6uapDHn21)

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

Why this is a false positive

The block fired during routine defensive email-security triage — reading message headers in an authorized mailbox to identify a phishing/business-email-compromise threat and produce an incident summary for the account owner. This is standard, in-scope blue-team work on systems the operator controls, with no offensive, evasive, or malicious component, yet the request was refused as a Usage Policy violation. The misclassification appears driven by surface terms common to both attacker and defender contexts (e.g. spoofing, compromised account, invoice lures), causing legitimate defensive analysis to be flagged.

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 2026-06-25T03:36:14.110Z.

Request IDs (lookup-able server-side)

• req_011CcPH3vmFMPzj6uapDHn21 (2026-06-25T03:36:14.110Z)

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.

Request ID: req_011CcPH3vmFMPzj6uapDHn21

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

---
_{🔎 Filed automatically by ClAudit v2.0.4 — a FOSS tool for reporting false-positive Claude Code blocks.}