Skip to content

Commit ecb3e54

Browse files
committed
Update CHANGELOG.md for 2.1.0 release
Version the changelog as 2.1.0 (was [Unreleased]), add Security section per Keep a Changelog convention, include missing items: GPT-4o Canvas prompt leak example, custom benchmark cache fix, release workflow fix. Add 2.0.0 baseline entry. https://claude.ai/code/session_01CDFqeg5QhB4V7yQ3yVVBc9
1 parent 1691909 commit ecb3e54

File tree

1 file changed

+12
-3
lines changed

1 file changed

+12
-3
lines changed

CHANGELOG.md

Lines changed: 12 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ All notable changes to this project will be documented in this file.
44

55
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
66

7-
## [Unreleased]
7+
## [2.1.0] - 2026-02-16
88

99
### Added
1010
- **RAG Poisoning Attack** ("Hidden Parrot Attack") — new fuzzing test that demonstrates how malicious instructions embedded in vector databases can compromise RAG system behavior
@@ -14,18 +14,23 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
1414
- Embedding configuration properties in `AppConfig` (`embedding_provider`, `embedding_model`, `embedding_ollama_base_url`, `embedding_openai_base_url`)
1515
- Configurable base URLs for Ollama and OpenAI providers (`ollama_base_url`, `openai_base_url`) with proper parameter transformation in chat clients
1616
- `TestStatus.report_skipped()` method and `skipped_count` tracking for tests that cannot run due to missing configuration or dependencies
17+
- GPT-4o with Canvas system prompt leak example (`system_prompt.examples/`)
1718
- Bandit security scanning workflow (`.github/workflows/bandit.yml`)
1819
- Dedicated test files: `test_app_config.py`, `test_prompt_injection_fuzzer_helpers.py`, `test_test_status.py`
1920

20-
### Fixed
21+
### Security
2122
- **[CRITICAL] CVE-2025-68664** — Upgraded langchain ecosystem (langchain, langchain-core, langchain-community) from 0.0.x to 0.3.x to fix serialization injection vulnerability that could allow secret extraction and arbitrary code execution
2223
- **[HIGH] CVE-2024-34062** — Upgraded tqdm from 4.66.1 to ≥4.66.3 to fix CLI arguments injection via `eval()`
23-
- **[HIGH]** httpx version pinned to `>=0.24.0,<0.25.0` to fix crashes caused by unpinned dependency (PR #65)
24+
- **[HIGH]** httpx version pinned to `>=0.24.0,<0.25.0` to fix crashes caused by unpinned dependency
25+
26+
### Fixed
2427
- ChromaDB `persist()` compatibility — gracefully handles ChromaDB 0.4.0+ which auto-persists
2528
- `register_test` decorator now properly returns the decorated class (was returning `None`)
2629
- Getter/setter consistency for `embedding_provider` and `embedding_model` — setters now accept empty values matching getter defaults
2730
- Empty base URL strings are now filtered out instead of being passed through to model constructors
2831
- Fragile error-message string matching in RAG poisoning replaced with specific exception type handling (`ImportError`, `ConnectionError`, `ValueError`, etc.)
32+
- Removed stale custom benchmark cache
33+
- Release workflow no longer overwrites manually written release notes
2934

3035
### Changed
3136
- Minimum Python version raised from 3.7 to 3.9 (required by langchain 0.3.x)
@@ -35,3 +40,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
3540
- Pydantic v1 field introspection → Pydantic v2 with v1 fallback
3641
- Test organization: AppConfig, helper function, and TestStatus tests moved from `test_is_response_list.py` into dedicated test files
3742
- Removed unused variable assignments in test code
43+
44+
## [2.0.0]
45+
46+
- Fuzzer 2.0 release

0 commit comments

Comments
 (0)