tools

v0.6.0 Security

This release includes 4 security fixes for security teams reviewing exposed deployments.

Published 13d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

This release patches 4 known CVEs

Topics

agentic agentic-ai agents ai anthropic autonomous-agents

+13 more

bedrock genai litellm llama llm machine-learning mcp multi-agent-systems ollama openai opentelemetry python strands-agents

Affected surfaces

rce_ssrf auth

ReleasePort's take

Light signal

editorial:auto 13d

Release v0.6.0 patches multiple security vulnerabilities: it blocks code execution in the calculator tool via restricted parsing and AST validation, adds consent gating plus newline sanitization to cron, and redacts credentials from AWS responses.

Why it matters: Patch immediately to prevent remote code execution in calculator, mitigate unauthorized cron command injection, and stop credential leakage from AWS APIs.

Summary

AI summary

Fixes security issues in calculator and cron tools, sanitizes AWS responses, skips hidden directories in file_read, and expands document location extraction in retrieve.

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Expand document location extraction for all RetrievalResultLocation types. Expand document location extraction for all RetrievalResultLocation types. Source: llm_adapter@2026-05-21 Confidence: low	—
Bugfix
Bugfix	Medium	Prevent code execution in calculator tool via restricted parse_expr. Prevent code execution in calculator tool via restricted parse_expr. Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Add consent gate and newline sanitization to cron tool. Add consent gate and newline sanitization to cron tool. Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Redact sensitive credentials in use_aws responses. Redact sensitive credentials in use_aws responses. Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Add AST validation to prevent code execution in calculator tool. Add AST validation to prevent code execution in calculator tool. Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Skip hidden directories during os.walk traversal. Skip hidden directories during os.walk traversal. Source: llm_adapter@2026-05-21 Confidence: low	—
Other	Medium	@opieter-aws made their first contribution. @opieter-aws made their first contribution. Source: llm_adapter@2026-05-21 Confidence: low	—

Full changelog

What's Changed

fix: prevent code execution in calculator tool via restricted parse_expr by @pgrayy in https://github.com/strands-agents/tools/pull/466
fix: add consent gate and newline sanitization to cron tool by @pgrayy in https://github.com/strands-agents/tools/pull/468
fix: redact sensitive credentials in use_aws responses by @pgrayy in https://github.com/strands-agents/tools/pull/467
fix: add AST validation to prevent code execution in calculator tool by @pgrayy in https://github.com/strands-agents/tools/pull/473
fix(file_read): skip hidden directories during os.walk traversal by @dosvk in https://github.com/strands-agents/tools/pull/440
feat(retrieve): expand document location extraction for all RetrievalResultLocation types by @opieter-aws in https://github.com/strands-agents/tools/pull/465

New Contributors

@opieter-aws made their first contribution in https://github.com/strands-agents/tools/pull/465

Full Changelog: https://github.com/strands-agents/tools/compare/v0.5.3...v0.6.0

Security Fixes

fix: prevent code execution in calculator tool via restricted parse_expr
fix: add consent gate and newline sanitization to cron tool
fix: redact sensitive credentials in use_aws responses
fix: add AST validation to prevent code execution in calculator tool

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track tools

Get notified when new releases ship.

About tools

A set of tools that gives agents powerful capabilities.

All releases →