[Bug][aup] Shodan exposure audit of own owned domains via API key wrongly blocked as policy violation (req_011CcGzvR2VyXSZy8555N3su)

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

Why this is a false positive

The request asks Claude to query a public internet-scan service ([REDACTED]) using the requester's own API key to enumerate exposure data about domains the requester owns, in order to assess that data and plan remediation. This is standard defensive attack-surface management on self-owned assets — no third-party targeting, exploitation, or unauthorized access is involved — yet it was blocked as a Usage Policy violation. The block appears triggered by surface keywords (API key, reconnaissance, "look up our data") rather than the actual intent, which is a benign, in-scope security self-audit.

A server-side safety/policy block fired during authorized, in-scope work in Claude Code.
Filing as a false positive. Recurred 2× across 1
session(s); first seen 2026-06-21T20:00:39.212Z.

Request IDs (lookup-able server-side)

• req_011CcGzvR2VyXSZy8555N3su (2026-06-21T20:00:39.212Z)
• req_011CcGzw49utqTMWQQzaWM2v (2026-06-21T20:00:42.333Z)

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_011CcGzvR2VyXSZy8555N3su

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

---
_{🔎 Filed automatically by ClAudit v2.0.21 — a FOSS tool for reporting false-positive Claude Code blocks.}