langchain 1.4.7

Source: https://github.com/langchain-ai/langchain
Tag scanned: langchain==1.4.7
Directory: libs/langchain_v1 (only this part of the repository was scanned)
Compared with: langchain==1.4.6 (0 signals introduced since)
Files: 166 scanned, 24 skipped (binary, oversized, or unrecognised)
Signals: 0 critical · 0 warn · 1 info
Scan time: 3.5 s
LLM review: Reviewed by claude-haiku-5-5 (Anthropic): 1 of 1 warn and critical signal; 1 demoted to info.
Disclude version: 4.1.0
Scanned (UTC): 2026-10-22 08:28

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 unit-test helper tool that evaluates an expression string with eval to demonstrate a non-emulated tool.
Reasoning
The eval call sits inside a test fixture tool that returns an f-string result. The comment and the explicit noqa S307 suppression show the developer knowingly used eval in a unit test. The snippet has no network, file, or obfuscation activity, and the expression comes from test-controlled input, so this looks like a legitimate test pattern rather than malicious code. Residual doubt: eval on a non-literal is risky if this test file were reused with untrusted input.

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 4.1.0
git clone https://github.com/langchain-ai/langchain langchain && cd langchain
git checkout langchain==1.4.7
disclude scan --severity info --diff langchain==1.4.6 libs/langchain_v1