This release includes 1 security fix for security teams reviewing exposed deployments.
Published 2mo
AI Agents & Assistants
✓ No known CVEs patched
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 summaryHard pins litellm<=1.82.6 to mitigate a supply chain attack
Full changelog
Pins litellm<=1.82.6 to supply chain attack - Supply 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<=1.82.6to 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
About harness-sdk
A model-driven approach to building AI agents in just a few lines of code.
Related context
Related tools
Beta — feedback welcome: [email protected]