Borehole · Project · free tier
nousresearch/hermes-agent
Free reading: not for reliance
290080e · 50,000 commits · 20,861 files
Read 2026-10-23

nousresearch/hermes-agent: technical due diligence, read from its repository

What Borehole read in nousresearch/hermes-agent's code and history at 290080e: 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 provenanceadequate
Engineering Process & SDLC Maturitystrong
Product & Engineering Maturityadequate
Security & Reliability Postureadequate
Observability & Operationsadequate
Fit with the Acquirernot assessable

Architecture & Codebase — including AI provenance

adequate
01.6

apps/desktop/electron/main.ts is 18,333 lines, 235× this codebase's median file

adequate

The median source file here is 78 lines. 284 files exceed 1,000 lines, the largest being 18,333. Size is not a defect on its own — some problems genuinely live in one place — but these are where merge conflicts, review fatigue and single-owner knowledge concentrate, and they are the first thing that slows an inheriting engineer down.

Evidence
apps/desktop/electron/main.ts:1 — 18,333 lines (235× median)
agent/auxiliary_client.py:1 — 8,393 lines (107× median)
plugins/platforms/discord/adapter.py:1 — 7,415 lines (95× median)
plugins/platforms/telegram/adapter.py:1 — 7,382 lines (94× median)
plugins/platforms/slack/adapter.py:1 — 6,956 lines (89× median)
01.15

1,110 errors caught and discarded in product code

adequate

1,110 places catch an error and do nothing with it, across 450 files (0.6 per thousand lines). Each is a failure the system will not report. They surface later as problems nobody can explain, and they are cheap to fix now.

Evidence
acp_adapter/auth.py:25 — error caught and discarded
acp_adapter/tools.py:149 — error caught and discarded
acp_adapter/tools.py:688 — error caught and discarded
01.42

1 model weight file committed directly to git

adequate

1 model weight files are stored in git itself, not in LFS, DVC or a model hub. Every clone carries them, the history keeps every version for good, and nothing records which run or data produced them.

Evidence
contributors/emails/ada.a0uew@56.pt — weights in git

Engineering Process & SDLC Maturity

strong

No finding.

Product & Engineering Maturity

adequate
04.3

82 direct dependencies in a single manifest

adequate

apps/desktop/package.json declares 82 direct dependencies. Each one is a maintenance obligation, a supply-chain surface and a potential licence question that transfers with the asset. The count says nothing about whether any given dependency was a good choice; it says how many such choices a buyer inherits.

Evidence
apps/desktop/package.json — 82 declared
pyproject.toml — 46 declared
web/package.json — 23 declared
apps/bootstrap-installer/package.json — 20 declared

Security & Reliability Posture

adequate
05.1

2 credential-shaped strings committed to the tree

adequate

Matches for Slack token appear in tracked files outside test and fixture paths. They stay in the history even after they leave the tree, so what matters is whether each was rotated. The code cannot tell whether any of them is live, and that decides whether this matters: none sits in production configuration, and none is in a format its provider keeps for live keys. Is any of these live? Show that each was rotated after it was committed, and when.

Evidence
2 cited: Slack token pattern matched
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
05.27

The build runs third-party code it does not pin

adequate

4 steps pipe a download straight into a shell. 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/bootstrap-installer.yml:42 — download piped into a shell
05.20

148 SQL statements built from strings

adequate

148 places in product code build SQL by formatting or joining strings rather than passing parameters, and in 65 of them a value, not a table or column name, goes into the string. Where any of those values comes from a request, it is an injection point. Each site needs a look; the fix, parameters, is small.

Evidence
agent/transcript_repair.py:74 — SQL built from a string
cron/executions.py:596 — SQL built from a string
cron/incidents.py:272 — SQL built from a string
05.21

19 shell commands built from strings

adequate

19 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.

Evidence
agent/command_token_source.py:55 — command run through a shell
apps/desktop/electron/main.ts:8840 — command run through a shell
cli.py:1251 — command run through a shell
05.22

5 deserialisers that can run code

adequate

5 places read data with a deserialiser that executes what it reads (`yaml.load` without a safe loader). That is safe on data the system wrote itself and remote code execution on anything else. Ask where each one's input comes from.

Evidence
plugins/security-guidance/patterns.py:44 — code-executing deserialiser
plugins/security-guidance/patterns.py:44 — code-executing deserialiser
plugins/security-guidance/patterns.py:146 — code-executing deserialiser
05.26

3 locked dependencies have published vulnerabilities, 2 high or critical in what ships

adequate

3 of 2,209 locked dependencies match 4 published advisories in OSV, 3 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 — brotlicffi 1.2.0.2: GHSA-9v8h-qqgm-4m35 (critical), fixed in 1.2.1.0; an optional extra
package-lock.json — zod 4.4.3: GHSA-mrhx-c7xc-m3w5 (high), fixed in 4.6.6
plugins/platforms/photon/sidecar/package-lock.json — zod 4.5.4: GHSA-mrhx-c7xc-m3w5 (high), fixed in 4.6.6
05.45

2 workload settings can give a container the host, behind a chart value or in a stack built from source

adequate

2 places run a container privileged or in the host's namespaces only when a Helm value switches them on, or in a compose file that builds the product from this repository, which is how it is developed rather than how it ships. Neither is on by default in what ships. Ask whether production sets the value or runs that stack.

Evidence
docker-compose.yml:35 — host access behind a setting or in a local stack
docker-compose.yml:67 — host access behind a setting or in a local stack
05.48

10 places insert HTML from a variable without sanitising it

adequate

10 places set HTML from a value that is neither a literal nor passed through a sanitiser. Where the value can come from a user, that is stored cross-site scripting, and it is the first thing a buyer's security review looks for in a frontend.

05.9

2 vendored components with no licence

adequate

Third-party code is committed into this repository without any statement of the terms it arrived under. Unknown terms are harder to deal with than inconvenient ones: an awkward licence can be complied with, an absent one cannot. Each of these needs its origin established before the code changes hands.

Evidence
native/fts5_cjk/vendor/sqlite3.h — 1 tracked files, no licence file
native/fts5_cjk/vendor/sqlite3ext.h — 1 tracked files, no licence file
05.65

15 advisories against this project in the last 24 months, 4 high or critical

adequate

The newest was published on 2026-10-21. A project that publishes advisories is telling its users about its fixes, and the count and pace say how much security work it carries. Whether 3 of them are fixed in the code you ship could not be told from this history: its version is only known to be at least 2026.9.24. Answer lives in: the release you run, set against each fixed version. The record is incomplete: NVD: 6 records name hermes-agent with nothing tying them to this repository (CVE-2026-10548, CVE-2026-108593, CVE-2026-18774, …).

Evidence
2026-10-21: CVE-2026-114463 (unrated): The webhook platform gateway in Nous Research Hermes Agent versions builds the session chat_id as webhook:{route_name}:{delivery_id} and re-derives the authoriz
2026-09-03: CVE-2026-71963 (high): Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS comman
2026-08-28: CVE-2026-82020 (high): Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to over
2026-08-28: CVE-2026-82021 (critical): Hermes Agent 0.18.2 prior to 0.19.0 contains a supply chain vulnerability in its bundled MCP catalog that allows a remote attacker to execute arbitrary code by
2026-08-06: CVE-2026-18976 (low): A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function get_tool_definitions of the file agent/agent_init.py of the

Observability & Operations

adequate
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
06.35

Sends usage data to telemetry.nousresearch.com by default

adequate

hermes_cli/config_defaults.py sends to telemetry.nousresearch.com, and agent/context_compressor.py leaves reporting on as shipped. Every installation reports to the vendor unless its operator turns this off. For a buyer running it inside their own product, that is an outbound data flow to a third party: ask what is sent, how often, and whether the buyer's customers were told.

Evidence
hermes_cli/config_defaults.py:2335 — reports to telemetry.nousresearch.com
agent/context_compressor.py:3792 — the reporting setting is on by default
06.18

2 of 2 deployed images carry no version, or `latest`

adequate

2 images in the deployment configuration are named without a version or as `latest`. A redeploy can change the software without a commit, a rollback has nothing to roll back to, and nobody can say from the repository what is running.

Evidence
docker-compose.windows.yml:25 — image without a version
docker-compose.yml:64 — image without a version

Fit with the Acquirer

not assessable

Not rated: structurally not assessable from a repository.

Read more, or read your own

The full report on nousresearch/hermes-agent: 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.