Bobby Tables but with LLM Apps - Google NotebookLM Data Exfiltration
The author reports that Google's NotebookLM is vulnerable to prompt injection via uploaded documents.
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 post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceGoogle’s NotebookLM
- Linked in sourcehere
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 reports that Google's NotebookLM is vulnerable to prompt injection via uploaded documents. A user-controlled field in a shared dataset can instruct the model to render an image whose URL carries data from other rows and documents, sending it to an attacker's server. The author states the issue was reported to Google in December 2023, that Google confirmed it, and that a fix for the image exfiltration vector was later deployed. The post recommends not rendering images or clickable links to arbitrary domains.
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 post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
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 post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
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.
A user who controls only their own profile field can inject a prompt that NotebookLM follows when another user analyzes the data.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe injected payload can make NotebookLM render an image URL that appends email and code values, exfiltrating them to an attacker server.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author says the attack can also pull data from a second uploaded document into the rendered URL.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe author reports Google confirmed the issue and deployed a fix for the image exfiltration vulnerability after publication.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
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 post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
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 untrusted data in shared documents can steer LLM apps into leaking other users' data through rendered images and links, a risk for any LLM tool that processes user-supplied records.
Limits and open questions
Source claims not independently checked; the post describes reproduction results that the author says became less reliable over time, and the fix status is the author's account.
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 →