Is CVE-2026-115415 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-115415 being exploited in the wild.

How severe is CVE-2026-115415?

High severity, with a CVSS score of 6.5, published 28 October 2026.

Which products and versions are affected?

AWS Strands Agents Tools 0.1.0 to 0.8.5; Strands Agents Tools 0.1.0 to 0.8.5.

How is CVE-2026-115415 attacked?

It is attacked over the network.

Am I affected by CVE-2026-115415?

Check whether you run Amazon AWS, AWS Strands Agents Tools or Strands Agents Tools at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-115415: Strands Agents Tools secret masking bypass in environment tool

CVE-2026-115415 · Severity: high · CVSS 6.5 · Published 2026-10-28

Strands Agents Tools is a Python package that provides pre-built tools for AI agents, including an environment tool for managing host environment variables. A flaw in the environment tool allows attackers to craft malicious prompts that instruct the AI model to disable secret masking, exposing unmasked environment variables including cloud credentials and API keys in cleartext. This could lead to compromise of cloud accounts and unauthorized API access.

Technologies: Amazon AWS. Vendors: Amazon, AWS.

Quick answers

Is CVE-2026-115415 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-115415 being exploited in the wild.
How severe is CVE-2026-115415?: High severity, with a CVSS score of 6.5, published 28 October 2026.
Which products and versions are affected?: AWS Strands Agents Tools 0.1.0 to 0.8.5; Strands Agents Tools 0.1.0 to 0.8.5.
Is there a fix for CVE-2026-115415?: Yes: fixed in 0.8.6. Until then: If immediate upgrade is not possible, remove the environment tool from your agents. Avoid running agents with long-lived cloud credentials or API keys in the process environment, and restrict outbound network access from the agent host to trusted endpoints only. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-115415 attacked?: It is attacked over the network.
Am I affected by CVE-2026-115415?: Check whether you run Amazon AWS, AWS Strands Agents Tools or Strands Agents Tools at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

Fixed in: 0.8.6

If immediate upgrade is not possible, remove the environment tool from your agents. Avoid running agents with long-lived cloud credentials or API keys in the process environment, and restrict outbound network access from the agent host to trusted endpoints only.

Technical details

The environment tool accepted a masking parameter from the LLM through its tool schema, allowing a crafted prompt to instruct the model to call the tool with masking disabled. This is an improper input neutralization vulnerability affecting the LLM prompting interface. An attacker can deliver a malicious prompt through agent input to trigger credential exposure without operator consent. The fix in version 0.8.6 moved masking control to the operator only, preventing the model from disabling it.

Affected products

Strands Agents Tools 0.1.0 to 0.8.5

Timeline

2026-10-28: disclosed

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.