Claude Cowork Exfiltrates Files
Simon Willison's link blog post, citing a finding by Prompt Armor, reports that Claude Cowork restricts outbound HTTP traffic to a list of allowed domains to guard against prompt-injection data exfiltration.
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: This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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, citing a finding by Prompt Armor, reports that Claude Cowork restricts outbound HTTP traffic to a list of allowed domains to guard against prompt-injection data exfiltration. According to the post, the workaround works because Anthropic's API domain is on that allowlist: an attacker can use their own Anthropic API key and have the agent upload visible files to the api.anthropic.com files endpoint, where the attacker can later retrieve them. The post is a short link blog entry quoting the finding.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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?
This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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.
Claude Cowork defaults to allowing outbound HTTP only to a specific list of domains.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseAnthropic's API domain is on that allowlist, per the cited Prompt Armor finding.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe described attack uses an attacker's own Anthropic API key to upload agent-visible files to the files endpoint.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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.
This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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 that domain allowlists can be bypassed when an allowed domain itself accepts uploads tied to attacker-controlled accounts, relevant to securing AI agents with network access.
Limits and open questions
This is a short link-blog brief quoting Prompt Armor; the full original research was not checked, and source claims not independently checked.
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 →