{"schema":"postcutoff/event@1","as_of":"2026-10-18T02:22:00+02:00","url":"https://postcutoff.com/e/2026-10-17-opencode-console-breach-provider-keys/","md":"https://postcutoff.com/e/2026-10-17-opencode-console-breach-provider-keys/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-17-opencode-console-breach-provider-keys","date":"2026-10-17","date_precision":"day","short_title":"OpenCode breach leaks stored provider API keys","deck":null,"takeaway":"On Oct 17, 2026 OpenCode (made by Anomaly Innovations) said a breach \"related to a large scale distillation attack\" hit about 1.4% of OpenCode Console users: those who had linked external providers, whose stored OpenAI, Anthropic and Google API keys were exposed.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":[{"n":1,"title":"OpenCode on X: breach notice (Oct 17)","url":"https://x.com/opencode/status/2111519637049319818","type":"official","group":"primary","domain":"x.com"},{"n":2,"title":"Startup Fortune: OpenCode breach exposes stored OpenAI and Anthropic keys, prompts urgent key rotation","url":"https://startupfortune.com/opencode-breach-exposes-stored-openai-and-anthropic-keys-prompts-urgent-key-rotation/","type":"press","group":"press","domain":"startupfortune.com"},{"n":3,"title":"Lydia Hallie (Anthropic) on X: Claude API keys revoked","url":"https://x.com/lydiahallie/status/2111563956666110287","type":"discussion","group":"reactions","domain":"x.com"}],"official":1,"filed":"2026-10-18","updated":"2026-10-18","orgs":["Anomaly Innovations","OpenCode","Anthropic","OpenAI","Google"],"title":"OpenCode Console breach exposes users' stored OpenAI, Anthropic and Google API keys in what the company calls a 'large scale distillation attack'","summary":"On Oct 17, 2026 OpenCode (made by Anomaly Innovations) said a breach \"related to a large scale distillation attack\" hit about 1.4% of OpenCode Console users: those who had linked external providers, whose stored OpenAI, Anthropic and Google API keys were exposed. The company is working with the three labs; Anthropic said it revoked Claude API keys it believed were affected. It is one of the first reported cases of a coding-agent service leaking frontier-model keys, apparently to obtain tokens for distillation.","key_facts":["OpenCode on X (Oct 17, 18:08 UTC, ~903k views): breach from 'a large scale distillation attack that impacted 1.4% of OpenCode Console users'; affected users emailed; only users with linked external providers affected; incident 'ongoing'; working with Anthropic, OpenAI and Google","Exposed: OpenAI, Anthropic and Google API keys saved in users' Console workspaces, from a 'legacy system' being shut down (per the company notice as reported by Startup Fortune)","Company: no evidence 'to date' that other data leaked; cannot confirm whether keys were used maliciously; advises revoking and reissuing keys in each provider's dashboard, checking usage from Oct 17 and setting spending limits","Anthropic's Lydia Hallie (Claude Code team, Oct 17): Anthropic worked with OpenCode and 'revoked Claude API keys we believe were affected'","Unverified user reports on X: unauthorized charges 'in the hundreds of dollars', a suspended Google Cloud project, an OpenAI account deleted for terms violations","Open questions: how attackers got in, how many accounts 1.4% is, and why it is called a distillation attack (commentators incl. Nathan Lambert asked whether it means stolen keys used to harvest model outputs)"],"key_numbers":[],"tags":["security","breach","api-keys","distillation","coding-agents","opencode"],"science":null,"body_md":"## What happened\n\nOpenCode, the open-source coding agent built by Anomaly Innovations, emailed affected users on Oct 17 and posted on X that a breach\ntied to \"a large scale distillation attack\" had hit about 1.4% of OpenCode Console users. Only users who had linked external\nmodel providers were affected; their stored provider API keys (OpenAI, Anthropic, Google) were exposed. The company said the\nincident was ongoing and that it was working with the three labs. Anthropic's Lydia Hallie said Anthropic had revoked the Claude API\nkeys it believed were affected. Startup Fortune reported that the keys came from a legacy system being shut down and that some users\nreported unauthorized charges; those reports are unverified.\n\nThe company did not explain the \"distillation\" label. A plausible reading, not confirmed by OpenCode, is that the attackers wanted\nother people's keys to pull large volumes of frontier-model outputs for training their own models while hiding behind many accounts.\n\n## Why it matters\n\nLabs have described distillation campaigns run through fake or resold accounts (see Anthropic's reports). This incident points to a\ndifferent supply route: stolen keys from third-party agent tools, where users pay the bill. It also shows the risk of storing frontier\nAPI keys in hosted consoles of agent tools.","disputed":[],"related":[{"id":"2026-10-12-anthropic-distillation-defenses","url":"https://postcutoff.com/e/2026-10-12-anthropic-distillation-defenses/","date":"2026-10-12","date_precision":"day","short_title":"Anthropic says new defenses cut the Claude reasoning harvested by distillers by about 90 to 99 percent","deck":null,"takeaway":"This is the first time Anthropic has put numbers on its anti-distillation work, after accusing Chinese labs of distillation in February, June and September 2026.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-10-13","updated":"2026-10-14","orgs":["Anthropic"]},{"id":"2026-02-23-anthropic-distillation-attacks-report","url":"https://postcutoff.com/e/2026-02-23-anthropic-distillation-attacks-report/","date":"2026-02-23","date_precision":"day","short_title":"Anthropic accuses DeepSeek, Moonshot and MiniMax of 'distillation attacks'","deck":"16M+ Claude exchanges via ~24,000 fraudulent accounts","takeaway":"\"Distillation attacks\" became a named security and policy issue in 2026.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":1,"filed":"2026-10-04","updated":"2026-10-04","orgs":["Anthropic","DeepSeek","Moonshot AI","MiniMax"]}],"people":[{"id":"nathan-lambert","name":"Nathan Lambert","url":"https://postcutoff.com/person/nathan-lambert/"}],"posts":[{"id":"2026-10-17-opencode-breach-notice","title":"OpenCode: breach from 'a large scale distillation attack' hit 1.4% of Console users","url":"https://postcutoff.com/p/2026-10-17-opencode-breach-notice/"},{"id":"2026-10-17-lydiahallie-opencode-keys-revoked","title":"Anthropic revoked Claude API keys believed affected by the OpenCode breach","url":"https://postcutoff.com/p/2026-10-17-lydiahallie-opencode-keys-revoked/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-18","type":"filed","text":"Created (OpenCode and Hallie posts read via fxtwitter; Startup Fortune)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-18","run":null,"sources_read":"OpenCode and Hallie posts read via fxtwitter; Startup Fortune","updated":"2026-10-18","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":170,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":109,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":200,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":139,"in_training_data":false}],"short_url":null}