Summer.fi paused its Lazy Summer vaults after roughly $6 million was drained through its Keeper AI rebalancing agents
At a Glance
- Catastrophic failure. Permanent data loss, major security breach, six-figure damages, or legal exposure.
Independent project · aggregated from public reports and may be unverified — see the primary source below · not affiliated with or endorsed by any company or product named.
What Happened
On 6 July 2026 at 05:17 UTC an exploit drained funds from Summer.fi's Lazy Summer vaults, whose asset rebalancing across vault contracts was handled by Keeper AI agents operating within governance-set constraints. Security firm Blockaid detected the attack while it was in progress and identified the exploit transaction, the exploiter address and the affected contracts. Blockaid estimated roughly $6 million drained at the time of detection. Summer.fi paused all vaults across the Lazy Summer Protocol while it investigated the root cause, with the final loss figure unsettled pending its incident review.
Case Analysis
Verified Facts
- The exploit began 6 July 2026 at 05:17 UTC against Summer.fi's Lazy Summer vaults
- Keeper AI agents were responsible for rebalancing assets across the vault contracts
- Blockaid estimated about $6 million drained at the time of detection
Not Publicly Confirmed
- The final confirmed loss after Summer.fi's incident review
- Whether the agent logic itself or an underlying contract was the root cause
Operational Lessons
- Automation layers sitting above audited smart contracts become the new, unaudited attack surface
- Agent-driven treasury operations need hard value caps and circuit breakers independent of the agent
Primary Source
Summer.fi exploit shows AI automation now sits above DeFi smart contract risk (CryptoSlate)cryptoslate.com ↗Case Record
More Cases
Klarna replaced 700 agents with an AI assistant, then started rehiring humans after service quality dropped
Klarna said in 2024 that its OpenAI-powered assistant did the work of 700 customer-service agents. By 2025 the company reversed course and began rehiring humans, with the CEO admitting they focused too much on cost and efficiency, which lowered quality. Klarna moved to a hybrid model where AI handles routine queries and people handle escalations and complex cases.
Cursor's command allowlist could be bypassed with shell built-ins, giving prompt injection a silent path to code execution
Pillar Security disclosed CVE-2026-22708 in Cursor. In Auto-Run Mode with an allowlist enabled, shell built-ins such as export, typeset, declare, readonly, unset and local were implicitly trusted by Cursor's server-side evaluator and executed without appearing in the allowlist or requiring approval, because they run inside the shell session rather than as separate binaries. An attacker delivering indirect prompt injection could silently poison environment variables and then trigger malicious code through trusted developer tools, producing both zero-click and one-click remote code execution. Pillar reported it in August 2025, Cursor acknowledged it as a systemic issue in September 2025, and the fix shipped in version 2.3 in January 2026, which now requires explicit approval for any command the parser cannot classify.
Prompt injection reached host-level code execution in Microsoft Semantic Kernel through eval() and a stray annotation
Microsoft disclosed two vulnerabilities that turn prompt injection into host compromise in its Semantic Kernel agent framework, which has over 27,000 GitHub stars. CVE-2026-26030 affects the Python package before 1.39.4: the default in-memory vector store filter is a Python lambda executed with eval() on unsanitized model-controlled input, so an attacker could escape the template string, traverse Python's class hierarchy, bypass the AST blocklist validator and run arbitrary commands, demonstrated by launching calc.exe from a single prompt injection. CVE-2026-25592 affects the .NET SDK before 1.71.0: DownloadFileAsync was accidentally marked with a [KernelFunction] attribute, exposing it to the model with an entirely AI-controlled, unvalidated local file path, allowing writes to locations such as the Windows Startup folder and thus sandbox escape.