Security Advisory: Anthropic's Slack MCP Server Vulnerable to Data Exfiltration
A security advisory describes a data leakage vulnerability in Anthropic's reference Slack MCP Server, which is now deprecated and unmaintained.
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: download counts and the proposed patch were not verified beyond the author's testing.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceintroduced MCP
- Linked in sourceon Github
- Linked in sourceAI agents that post to messaging apps
- Linked in sourceMany chat and messenger applications automatically
- Linked in sourcea few weeks ago
- Linked in sourcesecurity policy update
- Linked in sourcewidely used
- Linked in sourcerecent weekly download count is at 14k+
- Linked in sourcethe lethal trifecta
- Linked in sourcebut it is not seen as a security vulnerability by Anthropic as we have discussed in the past
- Linked in sourcehere
- Linked in sourcearchived the MCP server
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
A security advisory describes a data leakage vulnerability in Anthropic's reference Slack MCP Server, which is now deprecated and unmaintained. The server does not disable link unfurling when posting messages, so an AI agent manipulated by prompt injection can post a crafted hyperlink that causes Slack to request the URL and transmit embedded data to a third-party server. The author reports the issue to Anthropic on May 27, 2025, and says Anthropic archived the server on May 29, 2025 and agreed to public disclosure. Suggested mitigation is to set unfurl_links and unfurl_media to false.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; download counts and the proposed patch were not verified beyond the author's testing.
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; download counts and the proposed patch were not verified beyond the author's testing.
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.
Anthropic's reference Slack MCP Server does not disable link unfurling when posting messages.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseAn attacker can use prompt injection to make the agent post a link that leaks data such as .env secrets to an external server.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe vulnerability was reported May 27, 2025; Anthropic archived the server May 29, 2025 and will not patch it.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseSuggested mitigation is adding unfurl_links: false and unfurl_media: false to the post and reply functions.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; download counts and the proposed patch were not verified beyond the author's testing.
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; download counts and the proposed patch were not verified beyond the author's testing.
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 server is reportedly widely downloaded, so many installations may be exposed. Users who grant agents access to private data and untrusted content can have secrets exfiltrated without visible user action, and an unmaintained server will not receive official fixes.
Limits and open questions
Source claims not independently checked; download counts and the proposed patch were not verified beyond the author's testing.
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 →