// Security Advisory Triage

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

AWS security bulletins · published 2026-10-29 05:51 UTC
ACTION NEEDED VERIFY_EXPOSURE SECURITY
WHAT CHANGEDCVE-2026-115415 - Secret masking bypass in the environment tool in Strands Agents Tools. Source event: 2026-10-28T19:39:08+00:00. RSS discovery: 2026-10-29T05:49:06.016373+00:00.
WHY IT MATTERSThe captured feed identifies CVE-2026-115415. Check exposure against the affected product and versions; detailed remediation evidence is unavailable.
WHAT TO DOCheck your inventory for the product and affected versions named in this advisory. Remediation details were not captured; consult the vendor bulletin before changing configuration or applying a fix. Remediation: see bulletin https://aws.amazon.com/security/security-bulletins/2026-154-aws/ (retrieval attempted 2026-10-29T05:51:07.258Z; RSS discovery 2026-10-29T05:49:06.016373+00:00).
Deterministic source evidence; confidence not scored Primary source ↗ written by advisory-evidence-v2
Show the reasoning — raw diff, triage verdict, confidence
RSS DISCOVERY DIFF
+## CVE-2026-115415 - Secret masking bypass in the environment tool in Strands Agents Tools
+https://aws.amazon.com/security/security-bulletins/rss/2026-154-aws/
+Wed, 28 Oct 2026 19:39:08 +0000
+
+Bulletin ID: 2026-154-AWS Publication Date: 10/28/2026 12:30 PM PDT
+Description:
+We identified CVE-2026-115415, an issue where the environment tool accepted a masking parameter from the large language model (LLM) through its tool schema. A crafted prompt, delivered through content the agent is asked to process, could instruct the model to call the tool with masking turned off. The tool would then return the agent host's environment variables in cleartext, including cloud credentials and API keys, without prompting the operator for consent.
+Impacted versions: >= 0.1.0 AND < 0.8.6
+Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.
+Read this article
SEPARATE BULLETIN CAPTURE · unavailable

Retrieved separately from the RSS discovery; this does not establish historical page content.

retrieval attempted2026-10-29T05:51:07.258Z
captured atunavailable
sourcehttps://aws.amazon.com/security/security-bulletins/2026-154-aws/
content SHA-256unavailable
bulletin retrieval or evidence validation failed
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.95, needed 0.55
triage reasoningPrompt-injection vulnerability in AWS agent framework exposes cloud credentials without consent. Affects AI services in dependency trees.
signalsknown exploitation vector: prompt injection via LLM tool calls · credential exposure: cloud credentials and API keys leaked in cleartext · agent framework affected: Strands Agents Tools (AWS AI/agent SDK) · new CVE with fixed version: 0.8.6 available · affects dependency tree: agent frameworks are runtime dependencies for services using AI agents
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modeladvisory-evidence-v2 ($0.00000)