Breaking Claude Code Opus 5 Auto Mode
Simon Willison's link blog post discusses Anthropic's Claude Code auto mode, which Anthropic recently made the default for protecting users against prompt injection.
Source-based brief · Editor review not recorded · See checks and limits ↓
⚑ Recency not confirmed · what to check
We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news.
Claim context: the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
One primary source; other links are context, not independent corroboration.
- Primary sourcesimonwillison.net
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Recency not confirmed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Simon Willison's link blog post discusses Anthropic's Claude Code auto mode, which Anthropic recently made the default for protecting users against prompt injection. Willison cites researcher Johann Rehberger, who claims an attack against auto mode works 80% of the time by having Claude Code download and extract a zip archive, then execute code that imports a local struct.py file. In some runs, auto mode blocked Claude's cleanup command to terminate the malicious process. Willison agrees that sandboxing unattended agents is the safe approach.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Rehberger claims an attack against Claude Code auto mode works 80% of the time, per the post.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe attack tricks Claude Code into extracting a zip archive and executing a local struct.py via a base64 import.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseAuto mode blocked Claude's attempt to terminate the malware process in some runs, per the post.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseWillison concurs that unattended coding agents should run in containers or VMs with restricted network egress.
Source: simonwillison.net ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Simon Willison · Prompt Injection published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
It shows a safety classifier can itself contribute to failure, blocking remediation after a compromise. Teams relying on auto mode for agent protection may need sandboxing as a primary defense.
Limits and open questions
Source claims not independently checked; the 80% figure is Rehberger's claim as relayed by Willison, and the full Rehberger write-up was not reviewed.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →