Improper Neutralization of Input Used for LLM Prompting Affecting strands-agents-tools package, versions [0.1.0,0.8.6)


Severity

Recommended
0.0
medium
0
10

CVSS assessment by Snyk's Security Team. Learn more

Threat Intelligence

EPSS
0.34% (28th percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-PYTHON-STRANDSAGENTSTOOLS-22552224
  • published15 Nov 2026
  • disclosed28 Oct 2026
  • creditUnknown

Introduced: 28 Oct 2026

NewCVE-2026-115415  (opens in a new tab)
CWE-1427  (opens in a new tab)

How to fix?

Upgrade strands-agents-tools to version 0.8.6 or higher.

Overview

strands-agents-tools is an A collection of specialized tools for Strands Agents

Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the environment tool, where a prompt injection attack allows a remote actor to disable the tool's secret masking logic. By supplying a crafted prompt, an attacker can cause the agent to return the host's environment variables in cleartext, exposing cloud credentials and API keys that would otherwise be masked.

CVSS Base Scores

version 4.0
version 3.1