How Devin AI Can Leak Your Secrets via Multiple Means
The author describes how an attacker using indirect prompt injection can make the Devin AI agent leak secrets exposed as environment variables to third-party servers.
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 notes Devin's tools and integrations may have changed since testing in April 2025.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourcefirst post
- Linked in sourcelooked at Devin’s system prompt
- Linked in sourceChatGPT Operator earlier this year after I reported it
- Linked in sourcedemonstrated last year
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 how an attacker using indirect prompt injection can make the Devin AI agent leak secrets exposed as environment variables to third-party servers. The post lists four exfiltration vectors: shell commands such as curl, navigating the browser to attacker-controlled URLs with data appended, markdown image rendering from untrusted domains, and hyperlinks with invisible Unicode characters sent to Slack. The vulnerabilities were reported to Cognition in April 2025, and the author states that follow-up queries went unanswered.
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 notes Devin's tools and integrations may have changed since testing in April 2025.
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 notes Devin's tools and integrations may have changed since testing in April 2025.
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.
Shell and browser tools let Devin send environment variables to attacker-controlled servers when it processes injected instructions in a GitHub issue.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseDevin can render markdown images from untrusted domains, allowing sensitive data appended to an image URL to be leaked.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseInvisible Unicode tag characters can hide secrets in Slack output, which leak when a user clicks a link, according to the author's demonstration.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the author notes Devin's tools and integrations may have changed since testing in April 2025.
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 notes Devin's tools and integrations may have changed since testing in April 2025.
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 findings show that agentic systems with shell, browser, and messaging access can exfiltrate credentials when they read untrusted content, so defenses cannot rely on the model refusing harmful instructions.
Limits and open questions
Source claims not independently checked; the author notes Devin's tools and integrations may have changed since testing in April 2025.
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 →