AETERNAE AI RESEARCH LLC INDEPENDENT RESEARCH
ÆAETERNAERESEARCH
Sign inRequest access
← Malware catalog

Attributed metadata history

REPORTPUBLIC METADATA

Breaking Claude Code Opus 5 Auto Mode

In this post, we explore how a simple website summary request hijacks Claude Code Opus 5 in Auto Mode and achieves code execution with 60-80% attack success rate using a small sample size. This is interesting because a third-party evaluation commissioned by Anthropic showed a 0.00% prompt injection attack success rate for Opus 5 in Auto Mode. Auto Mode Is Now the Default in Claude Code Auto Mode replaces human approval prompts with a safety classifier. Since mid-August it is the default starting mode for Claude Code.

Reference details

Source category
research-report
First reported
Aug 27, 2026 04:00 UTC
Last reported
Aug 27, 2026 04:00 UTC
Catalog updated
Oct 14, 2026 02:57 UTC
Record ID
48b6900ebc17cd0f3d042f7225b60f1f70a4469e7f5c131c8f8767f64c7f59f5

Published indicators

Network indicators are visibly defanged. This page does not make them clickable or send them to another service.

No validated file hashes or network indicators are stored for this record.

Source observations

intelligence_src_c25d91fa3ad9ae9ac7

Source-provided label
Publisher RSS metadata
Evidence class
mentioned in report
Confidence
Not reported
Observed
Aug 27, 2026 04:00 UTC
Retrieved
Oct 14, 2026 02:57 UTC

This record contains metadata and attribution only. It does not host, download, unpack, render, or execute malware samples.

Feed collection status

Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.

1 sources: 0 stale, 0 needing attention, 0 paused, 0 unverified.

Review source update dates and status
  • intelligence_src_c25d91fa3ad9ae9ac7Recent successful batchLast successful batch: Last attempt:

Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.