Skip to content

harness-sdk

v1.33.0 Security

This release includes 1 security fix for security teams reviewing exposed deployments.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →
This release patches 1 known CVE

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

deps

Summary

AI summary

Hard pins litellm<=1.82.6 to mitigate a supply chain attack

Full changelog

Pins litellm<=1.82.6 to supply chain attack - S​upply Chain Attack in litellm 1.82.8 on PyPI

What's Changed

  • fix: summarization conversation manager sometimes returns empty response by @Unshure in https://github.com/strands-agents/sdk-python/pull/1947
  • fix: remove agent from swarm test to get more consistency out of it by @Unshure in https://github.com/strands-agents/sdk-python/pull/1946
  • fix: CRITICAL: Hard pin litellm<=1.82.6 to mitigate supply chain attack by @udaymehta in https://github.com/strands-agents/sdk-python/pull/1961

New Contributors

  • @udaymehta made their first contribution in https://github.com/strands-agents/sdk-python/pull/1961

Full Changelog: https://github.com/strands-agents/sdk-python/compare/v1.32.0...v1.33.0

Security Fixes

  • Hard pin litellm<=1.82.6 to mitigate supply chain attack (see https://futuresearch.ai/blog/litellm-pypi-supply-chain-attack/)

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

Track harness-sdk

Get notified when new releases ship.

Sign up free

About harness-sdk

A model-driven approach to building AI agents in just a few lines of code.

All releases →

Related context

Beta — feedback welcome: [email protected]