GHSA-782p-5fr5-7fj8: OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
lowvulnerabilityLLM-Specific
security
Summary
OpenClaw's Slack integration had a vulnerability where Slack channel descriptions could be injected into the AI model's system prompt (the instructions that tell the AI how to behave). This allowed attackers to use prompt injection (tricking an AI by hiding instructions in its input) to potentially trigger unintended actions or expose data if tool execution was enabled.
Solution / Mitigation
Upgrade to openclaw version 2026.2.3 or later. If you do not use the Slack integration, no action is required.
Vulnerability Details
EPSS (30-day exploit probability)
EPSS: 0.0%
Classification
Attack Type
Prompt Injection
Attack SophisticationTrivial
Impact (CIA+S)
integrityconfidentiality
Affected Vendors
Affected Packages
openclaw@< 2026.2.3 (fixed: 2026.2.3)
Related Issues
Original source: https://github.com/advisories/GHSA-782p-5fr5-7fj8
First tracked: February 17, 2026 at 02:12 PM
Classified by LLM (prompt v3) · confidence: 92%