Executive Summary
A breach of an OpenCode legacy system may have exposed OpenAI, Anthropic, and Google API keys saved in OpenCode Console. Organizations using the Console service or similar hosted AI workspaces should assess credential exposure and rotate potentially affected keys.
What Happened
An intruder reached a legacy system at OpenCode on the night of October 16 and may have exposed the third-party AI provider keys that users had saved in OpenCode Console, the company said. Console is OpenCode's optional hosted service: a workspace saves its own OpenAI, Anthropic, or Google key there, and Console uses that key to call the provider so team members can use the models without
Affected Products
- OpenCode Console
- OpenAI API keys
- Anthropic API keys
- Google API keys
Vulnerability / Attack Technique
Unauthorized access to a legacy system resulting in possible credential exposure
Technical Mechanism
An intruder reached a legacy OpenCode system on the night of October 16. OpenCode Console stores workspace-owned OpenAI, Anthropic, or Google keys and uses those keys to call the corresponding provider for team members; the article states that these stored keys may have been exposed.
AI Security Category
LLM02:2025 Sensitive Information Disclosure
Relevant Frameworks
RealGround Analysis
Teams running AI agents or LLM applications often depend on provider credentials held by hosted platforms and orchestration services. This incident illustrates the need to minimize stored secrets, isolate provider access, and maintain rapid credential-rotation procedures when an intermediary may be compromised.
Recommended Controls
- Rotate any OpenAI, Anthropic, or Google API keys that may have been stored in the affected OpenCode Console environment.
- Store provider credentials in a dedicated secrets manager rather than directly in application workspaces where possible.
- Apply least-privilege scopes, spending limits, environment restrictions, and separate keys for users, teams, and workloads.
- Monitor provider logs, usage, permissions, and billing for anomalous activity after suspected exposure.
- Maintain an incident-response procedure for revoking and replacing third-party AI credentials held by SaaS or orchestration platforms.
Related RealGround Service
AI Security Readiness Assessment · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/10/opencode-console-breach-may-have.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-19.