github Python analyzed 0be6770

dep0we/atomic-agents-stack

AI agents that live in your folder, not someone else's database. Vault-native, MIT-licensed. 21 spec docs + Python reference implementation.

maintainer: dep0we
license: MIT
first seen: 2026-06-04
last seen: 2026-07-28
releases · 30d: 0
short id

risk 100/100 · heuristic grade

E critical

vulnerabilities attested + 50
capability exposure inferred + 35
recent drift inferred + 20
tool safety inferred + 12
trust mitigators mixed − 3

attested inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 39s ago · see ecosystem CVEs →

risk trajectory 2 movements

6w ago C · 47 → E · 100
6w ago A · 0 → C · 47

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 3 CVEs · grade factor +50

HIGH

Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the c … affects ["<= 1.0.0"]

HIGH

Dashboard HTTP server path traversal allows arbitrary file read affects ["<= 1.0.0"]

HIGH

HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE) affects ["<= 1.0.0"]

tool safety 1 findings · grade factor +12

high dangerous code

committed secret: Anthropic key · dynamic exec: __import__(), unsafe yaml.load(), pickle.loads()

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 0be6770 · analyzer v28 · 2d ago

skills & prompt files 12

danger signals6

dynamic code execution __import__() dep0we-atomic-agents-stack-0be6770/atomic_agents/doctor.py :658 __import__(sdk_module)
dynamic code execution unsafe yaml.load() dep0we-atomic-agents-stack-0be6770/atomic_agents/registry/filesystem.py :649 frontmatter = yaml.load(frontmatter_text, Loader=_YamlLoader)
dynamic code execution pickle.loads() dep0we-atomic-agents-stack-0be6770/tests/test_llm_types_and_registry.py :362 restored = pickle.loads(pickle.dumps(err))
over-broad OAuth scope https://www.googleapis.com/auth/cloud-platform dep0we-atomic-agents-stack-0be6770/atomic_agents/doctor.py :778 scopes=["https://www.googleapis.com/auth/cloud-platform"]
committed secret Anthropic key dep0we-atomic-agents-stack-0be6770/tests/test_secret_backend_cli.py :65 sk-ant…(36 chars, redacted)
committed secret Anthropic key dep0we-atomic-agents-stack-0be6770/tests/test_secret_backend_protocol_conformance.py :519 sk-ant…(31 chars, redacted)

other grade factors evidence elsewhere

recent drift +20 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:dep0we/atomic-agents-stack/badge.svg)](https://mcpobservatory.com/servers/github:dep0we/atomic-agents-stack/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of dep0we.

dep0we/atomic-agents-stack

skills & prompt files 12

danger signals6

Navigate

Stream

Features

Display