Borehole · Project · free tier
zilliztech/deep-searcher
Free reading: not for reliance
ddc36db · 213 commits · 232 files
Read 2026-11-03

zilliztech/deep-searcher: technical due diligence, read from its repository

What Borehole read in zilliztech/deep-searcher's code and history at ddc36db: 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 Maturitystrong
Security & Reliability Postureadequate
Observability & Operationsadequate
Fit with the Acquirernot assessable

Architecture & Codebase — including AI provenance

strong

No finding.

Engineering Process & SDLC Maturity

strong

No finding.

Product & Engineering Maturity

strong

No finding.

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 232 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
Dockerfile — runs as root
05.13

6 outbound calls can wait forever

adequate

6 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.

Evidence
deepsearcher/embedding/jiekouai_embedding.py:117 — outbound call without a timeout
deepsearcher/embedding/novita_embedding.py:114 — outbound call without a timeout
deepsearcher/embedding/ppio_embedding.py:115 — outbound call without a timeout
05.26

39 locked dependencies have published vulnerabilities, 25 high or critical in what ships

adequate

39 of 391 locked dependencies match 136 published advisories in OSV, 60 of them rated high or critical. A lockfile says which version is installed, not whether the flawed code is reachable from this product, so each needs a look. Most are fixed by an upgrade, and the advisory names the version.

Evidence
uv.lock — pillow 10.4.0: GHSA-332p-7hrc-92wf (critical), fixed in 13.0.0
evaluation/jev_stopping/uv.lock — pillow 12.3.0: GHSA-332p-7hrc-92wf (critical), fixed in 13.0.0
uv.lock — crawl4ai 0.6.2: GHSA-2jq4-q6vv-4cp3 (critical), fixed in 0.9.0; an optional extra
05.65

1 advisory against this project in the last 24 months

adequate

The newest was published on 2026-06-08. 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
2026-06-08: GHSA-43px-gpwc-q84v (low): zilliztech deep-searcher has an Incorrect Privilege Assignment issue

Observability & Operations

adequate
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 210 files for 10 structured logging libraries; 0 matched
06.8

One request cannot be followed through the logs

adequate

Nothing in the service carries a request or correlation id, and there is no tracing. When a customer reports a failure, the log lines that belong to their request cannot be picked out from everyone else's.

Evidence
no request id, correlation id or tracing found
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 zilliztech/deep-searcher: 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.