Not Just OpenAI: Anthropic Says Claude Hacked 3 Organizations
"Because of this, when Claude’s search led it to real systems on the open internet, it treated them as part of the exercise."Claude then breached each affected organization's system via standard hacking methods, such as weak passwords and unauthenticated endpoints. It didn't name them.What is Anthropic doing to stop this from happening again? About Our Expert James Peckham Reporter Experience I’ve been a journalist for over a decade after getting my start in tech reporting back in 2013.
- ▪"Because of this, when Claude’s search led it to real systems on the open internet, it treated them as part of the exercise."Claude then breached each affected organization's system via standard hacking methods, such as weak passwords and u
- ▪It didn't name them.What is Anthropic doing to stop this from happening again?
- ▪About Our Expert James Peckham Reporter Experience I’ve been a journalist for over a decade after getting my start in tech reporting back in 2013.
2 outlets in our directory ran this story, first to last over 6 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
PCMag files mainly under tech. We currently carry 350 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | PCMag |
| Canonical URL | https://www.pcmag.com/news/not-just-openai-anthropic-says-claude-escaped-tests-to-hack-3-organizations |
| Publication time | Fri, 31 Jul 26 13:04:02 +0000 |
| Retrieval time | 2026-07-31T15:03:09.041Z |
| Last seen | 2026-07-31T15:03:09.041Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 4bscw1GekKuR · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Anthropic has discovered that Claude AI models unknowingly "gained unauthorized access to the real systems of three different organizations."Prompted by OpenAI's disclosure that its internal models had escaped a sandboxed test environment and breached the open-source machine learning model platform Hugging Face, Anthropic reviewed "141,006 evaluation runs where Claude could have obtained internet access." It found "three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations."These incidents involved six total runs, four of which were from the same organization.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PCMag.
Discussion
0 commentsMore from PCMag
