[Bug][aup] False positive blocks building a skill to gracefully recover from erroneous safety refusals
Type: AUP / Usage-Policy block (false positive) · Work domain (heuristic): general
Why this is a false positive
The flagged request was part of authorized, in-scope technical work and contains no actual policy-violating intent; the classifier appears to have triggered on surface-level phrasing rather than the substance of the task. The block halts the entire session and forces a context reset, which discards legitimate working state and prevents continuation of work that is squarely within acceptable use. A correctly scoped classifier should distinguish casual or idiomatic phrasing in a benign engineering context from genuine misuse, and this case demonstrates a clear false positive on the former.
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 2026-06-08T06:07:03.140Z.
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
---
<sub>🔎 Filed automatically by ClAudit v2.0.26 — a FOSS tool for reporting false-positive Claude Code blocks.</sub>