Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit)
The author reports that Windsurf Cascade's create_memory tool can be invoked automatically during an indirect prompt injection, without human approval.
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 author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceSpAIware is an attack we first successfully demonstrated with ChatGPT last year
- Linked in sourcesystem prompt
- Linked in sourceSpAIware exploit demonstrated with ChatGPT from last year
- Linked in sourceSpAIware & More: Advanced Prompt Injection Exploits in LLM Applications
- Linked in sourcecorresponding blog post about AI Domination
- Linked in sourcedata exfiltration vulnerabilities described in previous posts
- Linked in sourceWindsurf’s CEO goes to Google; OpenAI’s acquisition falls apart
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 Windsurf Cascade's create_memory tool can be invoked automatically during an indirect prompt injection, without human approval. Malicious instructions planted in source code comments can persist long-term memories that affect future chat sessions and enable continuous data exfiltration. The author disclosed the issue to Windsurf on May 30, 2025, and withheld technical details and the video until fixes are deployed. Windsurf acknowledged the report and said it would work on fixes.
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 author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
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 author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
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.
Windsurf Cascade's create_memory tool is automatically invoked during an indirect prompt injection without requiring human approval.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseInjected instructions can persist into future chat sessions, potentially adding backdoors or false information.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author demonstrated that a 1-pixel transparent image can hide data exfiltration from the user interface.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseWindsurf acknowledged the disclosure and said it will work on fixes, with no ETA given.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
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 author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
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
Persistent memory lets a single prompt injection compromise all future conversations, not just one session. Users and developers using agentic coding tools should review stored memories and watch for unexpected entries.
Limits and open questions
Source claims not independently checked; the author withheld payloads and full technical details, and the proof of concept is not fully reproducible from the text.
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 →