Incident report · Supply chain
OpenCode Console Breach May Have Exposed OpenAI, Anthropic, and Google API Keys
On October 16, an intruder accessed a legacy system at OpenCode, a third-party AI provider. This breach may have exposed OpenAI, Anthropic, and Google API keys saved by users in OpenCode Console, the company's hosted service. These keys allowed team members to access various AI models. The full extent of the data exfiltration remains under investigation.
- Discovered
- Oct 19 2026
- Failure mode
- Supply chain
- Source
- The Hacker News · Oct 19 2026
- Impact
- Exposure of OpenAI, Anthropic, and Google API keys saved by users in OpenCode Console.
Summary from the public record. The failure mode’s analysis follows.
The agent was fine. Everything it trusted was not.
How Fencio prevents this
The agent trusted a component it had never verified: a package, an extension, a skill, or a server that looked legitimate. When that component changed or was compromised, the agent carried the payload straight into a trusted environment.
Fencio inventories every tool, server, and skill an agent can reach, pins their versions and declared capabilities, and blocks calls when a component starts doing something its manifest never declared, like reading env files or mailing new recipients.
Runtime policy example · Supply chainLive
- 12:17:23mcp.tool upload_file(.env)Capability not in pinned manifestBlock
- 12:20:40mcp.tool lint(src/)Manifest match · v1.4.2Allow
- 12:23:57pkg.install(unverified-name)Package not in approved registryBlock
Say yes to the AI your business wants.
Book a 30-minute call. Bring your agents and your rules.