langchain 1.4.5

Source: https://github.com/langchain-ai/langchain
Tag scanned: langchain==1.4.5
Directory: libs/langchain_v1 (only this part of the repository was scanned)
Compared with: langchain==1.4.4 (0 signals introduced since)
Files: 166 scanned, 24 skipped (binary, oversized, or unrecognised)
Signals: 0 critical · 0 warn · 1 info
Scan time: 3.2 s
LLM review: Reviewed by claude-haiku-5-5 (Anthropic): 1 of 1 warn and critical signal; 1 demoted to info.
Disclude version: 4.0.0
Scanned (UTC): 2026-10-14 18:43

Signals

Ordered by severity, then signals introduced in this release. Hidden characters are shown as ⟨U+…⟩.

info ~~warn~~ → info by review dynamic-execution libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_tool_emulator.py:47:23

`eval` called on a non-literal expression (ast pass, confidence 0.70)
```
    # This tool executes normally (not emulated)
    return f"Result: {eval(expression)}"  # noqa: S307
```
likely benign LLM, confidence 0.85 A test-only mock tool that evaluates an expression with eval, with a lint suppression, inside a unit test for tool emulation.
Reasoning
The eval call sits inside a test-fixture tool in a unit test file for a tool emulator. The comment says this tool runs normally and is not emulated, and the `# noqa: S307` marker shows the lint suppression was deliberate. The expression comes from the test's own inputs, not from untrusted external data, and nothing in the snippet shows a dropper, network activity, or obfuscation. The residual risk is that eval on arbitrary input is unsafe if this pattern were copied into production code.

Reproduce This Scan

Run disclude locally to verify. Add --format sarif for SARIF output. Add --llm (with an API key in the environment) to include the LLM review.

cargo install disclude --version 4.0.0
git clone https://github.com/langchain-ai/langchain langchain && cd langchain
git checkout langchain==1.4.5
disclude scan --severity info --diff langchain==1.4.4 libs/langchain_v1