CVE-2026-115415

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

CVE-2026-115415 Secret masking bypass in the environment tool in Strands Agents Tools

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

CVE-2026-115415

The Strands Agents Tools software, in versions prior to 0.8.6 , contains an improper neutralization of input used for LLM prompting within the environment tool . This vulnerability allows remote actors to bypass the tool's secret masking functionality using a crafted prompt. Successful exploitati...

CVE-2026-115415 Secret masking bypass in the environment tool in Strands Agents Tools

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

CVE-2026-115415

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

EUVD-2026-112407

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

amazon-nova-act-mcp (>=1.0.60.0, <=1.20260527102944.0), gherkai-worker-novaact (>=1.4.0, <=1.4.9) +5 more potentially affected by CVE-2026-115415 via strands-agents-tools (>=0.1.9, <=0.2.22)

strands-agents-tools PYPI version =0.1.9, =1.0.60.0, =1.4.0, =2.3.18.0, =0.1.0, =0.1.0, =0.1.0, =0.1.6 Source cves: CVE-2026-115415 Source advisory: MEND:CVE-2026-115415...

Strands Agents Tools prompt injection vulnerability

Versions of Strands Agents Tools prior to 0.8.6 contain a prompt injection vulnerability. This flaw stems from improper handling of inputs used in LLM prompts within the environment tool; it may allow remote attackers to disable the tool’s confidential masking via specially crafted prompts. As a...

CVE-2026-115415: Undefined Security Weakness

Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's...

PT-2026-129166

Name of the Vulnerable Software and Affected Versions Strands Agents Tools versions prior to 0.8.6 Description Improper neutralization of input used for LLM prompting in the environment tool allows remote actors to obtain the agent host's environment variables in cleartext, including cloud...

gotrain (1.0.0), strands-agents-builder (>=0.1.0, <=0.1.6) +1 more potentially affected by unknown CVE via strands-agents (0.3.0)

strands-agents PYPI version 0.3.0 is affected by a known vulnerability. The following packages have a transitive dependency on strands-agents and may be impacted: - gotrain 1.0.0 - strands-agents-builder =0.1.0, =0.1.0, =0.1.9 Source cves: unknown CVE Source advisory: OSV:GHSA-3W55-933P-8PV5...

gotrain (1.0.0), strands-agents-builder (>=0.1.0, <=0.1.6) +1 more potentially affected by CVE-2026-115419 via strands-agents (0.3.0)

strands-agents PYPI version 0.3.0 is affected by a known vulnerability. The following packages have a transitive dependency on strands-agents and may be impacted: - gotrain 1.0.0 - strands-agents-builder =0.1.0, =0.1.0, =0.1.9 Source cves: CVE-2026-115419 Source advisory: OSV:GHSA-4V6F-7VJH-6X4M...

Improper Neutralization of Input Used for LLM Prompting

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 pythonrepl function in src/strandstools/pythonrepl.py. An attacker can execute arbitrary...

amazon-nova-act-mcp (>=1.0.60.0, <=1.20260527102944.0), gherkai-worker-novaact (>=1.4.0, <=1.4.9) +5 more potentially affected by CVE-2026-78379 via strands-agents-tools (>=0.1.9, <=0.2.22)

strands-agents-tools PYPI version =0.1.9, =1.0.60.0, =1.4.0, =2.3.18.0, =0.1.0, =0.1.0, =0.1.0, =0.1.6 Source cves: CVE-2026-78379 Source advisory: SNYK:PYTHON-STRANDSAGENTSTOOLS-19329790...

CVE-2026-78379

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

EUVD-2026-65735

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

amazon-nova-act-mcp (>=1.0.60.0, <=1.20260527102944.0), gherkai-worker-novaact (>=1.4.0, <=1.4.9) +5 more potentially affected by CVE-2026-78379 via strands-agents-tools (>=0.1.9, <=0.2.22)

strands-agents-tools PYPI version =0.1.9, =1.0.60.0, =1.4.0, =2.3.18.0, =0.1.0, =0.1.0, =0.1.0, =0.1.6 Source cves: CVE-2026-78379 Source advisory: MEND:CVE-2026-78379...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...