Skip to content
Registry/APM-0081
APM-00814SEVEREReported July 20, 2026

Hidden text on a web page could rewrite AWS Kiro's MCP config and run code on the developer's machine

Agent Involved
Kiro
Estimated Damage
Not quantified
Severity
4 / 5 Severe
Impact Band
Serious damage. Customer data affected, security incident, or financial losses $10k–$100k.

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.

Intezer disclosed CVE-2026-10591 in AWS's agentic IDE Kiro. An attacker could hide instructions in a web page that Kiro fetches during a task, and the agent would rewrite its own Model Context Protocol configuration file without asking for user approval. Because MCP server entries specify commands to execute, the rewritten config gave the attacker arbitrary code execution on the developer's machine. AWS confirmed the fix shipped in Kiro 0.11.130, issued security bulletin 2026-037-aws, and recommended users update.

Verified Facts

  • CVE-2026-10591 let hidden web-page instructions rewrite Kiro's MCP configuration without user approval
  • A rewritten MCP config yields arbitrary code execution because entries specify commands to run
  • AWS patched it in Kiro 0.11.130 and published security bulletin 2026-037-aws

Not Publicly Confirmed

  • Whether the flaw was exploited in the wild

Operational Lessons

  • An agent's own configuration files must be outside the set of files it can write during a task
  • Any file that defines executable commands deserves an explicit, unskippable human approval gate
Remote Code Execution in AWS Kiro, CVE-2026-10591 (Intezer)research.intezer.com
Case No.
APM-0081
Reported
July 20, 2026
Attribution
Anonymous
Discussion

More Cases

0
APM-0070OpenAI3MODERATE
May 18, 2025

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.

0
APM-0083Cursor3MODERATE
Jan 14, 2026

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.

0
May 7, 2026

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.