[Bug][aup] Block stopped phishing/BEC triage of user's own mailbox: identifying compromised internal account s (req_011CcPH3vmFMPzj6uapDHn21)

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

Why this is a false positive

Claude Code refused a request that was part of authorized email security triage — reviewing message headers in a mailbox the operator administers to identify phishing and a likely compromised internal account. The work is standard defensive incident response on systems the user controls, with the analysis driven entirely by inspecting headers of already-received mail; no offensive technique, targeting of third parties, or policy-violating activity was requested or performed. The block appears triggered by surface-level phishing/spoofing terminology rather than the actual intent, making it a false positive on legitimate in-scope defensive work.

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 v2.0.3 — a FOSS tool for reporting false-positive Claude Code blocks.}