Exfiltrating Your ChatGPT Chat History and Memories With Prompt Injection
The author describes a bypass of OpenAI's url_safe rendering feature that allows ChatGPT to send personal information, including chat history, to a third-party server via prompt injection in untrusted content such as websites or PDFs.
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 full exploit payload was not published and the fix status rests on the author's update.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourcereviewing
- Linked in sourceOpenAI introduced
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
The author describes a bypass of OpenAI's url_safe rendering feature that allows ChatGPT to send personal information, including chat history, to a third-party server via prompt injection in untrusted content such as websites or PDFs. The author reports using an Azure Blob Storage domain that is considered url_safe as the exfiltration channel. The post says the issues were reported to OpenAI in October 2024, that the root cause was reported over two years earlier, and that the vulnerability was addressed by OpenAI on August 26, 2025. The author withheld the full prompt injection payload.
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 full exploit payload was not published and the fix status rests on the author's update.
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 full exploit payload was not published and the fix status rests on the author's update.
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.
The author reports that url_safe bypasses reported in October 2024 remained unfixed when the research was conducted.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphrasePrompt injection in untrusted content such as a website or PDF could cause chat context, including chat history, to be sent to a third-party server.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author used an Azure Blob Storage domain on a url_safe-allowed domain, whose server logs let the attacker observe the leaked data.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe post states the vulnerability was addressed by OpenAI on August 26, 2025, and withholds the full exploit payload.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the full exploit payload was not published and the fix status rests on the author's update.
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.
Embrace The Red published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; the full exploit payload was not published and the fix status rests on the author's update.
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
The report describes a concrete data-leakage path in an AI assistant's link-rendering safeguards, showing how prompt injection from untrusted documents can expose user conversation data to attackers.
Limits and open questions
Source claims not independently checked; the full exploit payload was not published and the fix status rests on the author's update.
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 →