Borehole · Project · free tier
chatchat-space/langchain-chatchat
Free reading: not for reliance
49165d6 · 2,471 commits · 523 files
Read 2026-10-23

chatchat-space/langchain-chatchat: technical due diligence, read from its repository

What Borehole read in chatchat-space/langchain-chatchat's code and history at 49165d6: its licence, security advisories, releases, review practice, tests, dependencies and operations. Every finding cites the file and line it rests on. The full report also covers the team and asks the questions the code cannot answer.

DimensionRating
Architecture & Codebase — including AI provenancestrong
Engineering Process & SDLC Maturitystrong
Product & Engineering Maturityadequate
Security & Reliability Postureadequate
Observability & Operationsadequate
Fit with the Acquirernot assessable

What the repository says

  • .gitmodules:1: 1 submodule(s) this survey does not read: chatchat/chatchat/data/knowledge_base/samples/content/wiki

Architecture & Codebase — including AI provenance

strong
01.3

Commit messages are templated rather than written

adequate

41% of commit subjects are exact repeats of another subject, and subject length varies by only 39.1 characters. A log written by someone explaining their reasoning to a future reader does not look like this. The log is therefore weak evidence of intent, whatever the code is like.

Evidence
164× 'Update README.md'
135× 'Add files via upload'
80× 'update README.md'

Engineering Process & SDLC Maturity

strong
02.6

Almost no process scaffolding exists in the repository

adequate

Of five ordinary markers — CI workflows, CODEOWNERS, a pull-request template, pre-commit hooks, contribution guidance — 1 is present: CI workflows. Branch protection itself is a GitHub setting rather than a file, so this is a reading of proxies and not of the rules themselves. What it does establish is that the process is not written down anywhere a new engineer would find it.

Evidence
1 of 5 markers present across 523 tracked files

Product & Engineering Maturity

adequate
04.19

10% of bug fixes add or change a test

adequate

Of 83 fixes in the last 24 months, 8 touched a test. A fix without the test that would have caught the bug can quietly come back, and the suite never learns from what went wrong.

Evidence
8 of 83

Security & Reliability Posture

adequate
05.2

None of the standard security guard rails are configured

adequate

There is no disclosure policy, no automated dependency updates, no named code owners and no pre-commit configuration. None of these is load-bearing on its own. Their collective absence says that security posture here is whatever the current team happens to remember to do, which is not a posture that survives the team changing.

Evidence
checked 5 kinds of guard rail across 523 tracked files; 0 present
05.6

1 Dockerfile runs the application as root

adequate

No USER instruction switches away from root, so the process runs with full privileges inside the container. It is a one-line fix and an ordinary expectation, which is why its absence is worth asking about: it usually says more about whether anyone has reviewed the deployment than about this container specifically.

Evidence
docker/Dockerfile — runs as root
05.25

1 environment file is committed

adequate

libs/chatchat-server/.env is tracked in git. Environment files are where credentials usually live, and committing one usually means nobody decided how secrets reach the running application. Whatever is in it is in the history for good. Check 05.1 says whether it holds anything credential-shaped.

Evidence
libs/chatchat-server/.env — committed environment file
05.27

The build runs third-party code it does not pin

adequate

8 third-party CI actions are referenced by a tag or branch rather than a commit, so they run whatever that tag points to on the day. Tags have been moved to malicious commits in real supply-chain attacks, and a piped script is whatever the server returns that minute. Pinning to a commit is the fix, and it is small.

Evidence
.github/workflows/_release.yml:202 — action pinned by tag
.github/workflows/_release.yml:249 — action pinned by tag
05.13

5 outbound calls can wait forever

adequate

5 HTTP calls use a client with no timeout (Python `requests` without `timeout=`, or Go's default client). When a dependency slows down, each one holds a worker until the connection gives up, and enough of them take the service down with the dependency.

05.20

3 SQL statements built from strings

adequate

3 places in product code build SQL by formatting or joining strings rather than passing parameters. In each, what the code shows going in is a table or column name, a constant, or something the line does not show, not a request's value. Ask whether any value reaches these strings, rather than a parameter.

05.21

9 shell commands built from strings

adequate

9 places run a command through a shell (`shell=True`, `os.system`, `exec` with a template) rather than passing arguments. Where any part comes from outside, it is command injection. Ask where each one's input comes from.

05.45

2 workload settings give a container the host

adequate

2 places in the deployment configuration run a container privileged or in the host's network, process or IPC namespace. A compromise of that container is a compromise of the machine, and most acquirers' security reviews block it. Node agents (network, storage, monitoring) are excluded.

Evidence
docker/docker-compose.yaml:9 — privileged or host namespace
docker/docker-compose.yaml:34 — privileged or host namespace
05.8

Manifest says MIT, licence file says Apache-2.0

adequate

pyproject.toml declares MIT. LICENSE contains the text of Apache-2.0. Package managers and downstream users read the first; auditors and acquirers read the second. One of them is wrong, and until it is settled the terms this code is offered under are genuinely ambiguous.

Evidence
pyproject.toml:6 — declares MIT
LICENSE — text of Apache-2.0
05.65

8 advisories against this project in the last 24 months, 1 high or critical

adequate

The newest was published on 2026-10-01. A project that publishes advisories is telling its users about its fixes, and the count and pace say how much security work it carries.

Evidence
2026-10-01: CVE-2026-51884 (critical): The /knowledge_base/upload_temp_docs temporary document upload endpoint in Langchain Chatchat 0.3.1 is vulnerable to path traversal. By crafting malicious filen
2026-05-05: GHSA-jv4p-mhmp-69vw (low): Langchain-Chatchat Uses Insufficiently Random Values
2026-05-05: GHSA-wmvv-fhm6-w34x (low): Langchain-Chatchat Uses a Broken or Risky Cryptographic Algorithm
2026-05-05: GHSA-x229-w2j4-h748 (low): Langchain-Chatchat has a Race Condition in its OpenAI-Compatible File Upload API
2026-05-05: CVE-2026-7844 (low): A vulnerability was detected in chatchat-space Langchain-Chatchat up to 0.3.1.3. This vulnerability affects the function files/list_files/retrieve_file/retrieve

Observability & Operations

adequate
06.1

No telemetry or error reporting is wired in anywhere

adequate

None of 421 readable files references an instrumentation, metrics or error-reporting library. If this system is in production, nobody learns that it broke from the system itself — they learn it from a customer. That is a reliability finding before it is an observability one.

Evidence
searched 421 tracked text files for 16 known instrumentation libraries; manifests for metrics, tracing and error-reporting families; locked dependencies for the packages that emit; 0 matched
06.2

No structured logging library is in use

adequate

Nothing references a structured logging library. Logs that are written to be read by a person are not searchable by a machine, which means incident response here is proportional to how well someone remembers the codebase rather than to what the tooling can find.

Evidence
searched 421 files for 10 structured logging libraries; 0 matched
06.9

No error reporter is wired in

adequate

Nothing in the service initialises an error reporter (Sentry, Rollbar, Bugsnag, Honeybadger or an APM agent). An exception in production reaches a person only if someone is reading the logs, which usually means a customer reports it first.

Evidence
no error reporter initialised

Fit with the Acquirer

not assessable

Not rated: structurally not assessable from a repository.

Read more, or read your own

The full report on chatchat-space/langchain-chatchat: every dimension, the questions for the room, and the audit log.

Survey a repository: free on public repositories. Private code is read on your own machine by a collector whose source you can read first.