Track vulnerabilities like this one. Sign up free to get alerted when software you use is affected.

Slack Messages Can Be Injected in OpenClaw

published 6 months ago

Summary

OpenClaw versions before 2026.4.2 allow unauthorized Slack messages to be injected into conversations, potentially allowing attackers to manipulate model context and bypass security controls. This is a security risk because it could be used to spread malicious messages or disrupt conversations. To stay secure, update to version 2026.4.2 or later.

What to do

Update GitHub Actions openclaw to version 2026.4.2.

Affected software

Ecosystem	Vendor	Product	Affected versions
npm	GitHub Actions	openclaw	< 2026.4.2 Fix: upgrade to 2026.4.2

Original advisory text

Duplicate Advisory: OpenClaw: Slack thread context could include messages from non-allowlisted senders

### Duplicate Advisory
This advisory has been withdrawn because it is a duplicate of GHSA-qm77-8qjp-4vcm. This link is maintained to preserve external references.

### Original Description
OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages to enter agent context. Attackers can inject unauthorized thread messages through allowlisted user replies to bypass sender access controls and manipulate model context.

References

Fix within

Internet-facing 60 days

Internal At next upgrade

Not known to be exploited
Needs hands-on effort to exploit (estimated)
Gives an attacker partial control (estimated)

Severity

2.3 Low

Type

CWE-346Origin Validation Error

Timeline

Published24 Apr 2026

Updated4 May 2026

First seen4 May 2026

Sources

GHSA-7hrg-5w46-5r2x · GHSA

Track software like this

Free during beta