From ticket to reviewed pull request. Free and open-source, on your machine.
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 11
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.
grade last moved 1w ago · see ecosystem CVEs →
- C · 44 → C · 36
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key · dynamic exec: pickle.loads(), __import__ sink, eval()/exec()
analyzed commit 1d7edf4 · analyzer v33 · 25m ago
skills & prompt files 3
danger signals18
- dynamic code execution pickle.loads() no-human-ai-no_human-1d7edf4/eval/commit0_corpus/vendor/cachetools-5.5.2/tests/__init__.py :272
cache = pickle.loads(pickle.dumps(source)) - dynamic code execution pickle.loads() no-human-ai-no_human-1d7edf4/eval/commit0_corpus/vendor/cachetools-5.5.2/tests/test_keys.py :89
pickled = pickle.loads(pickle.dumps(k)) - dynamic code execution __import__ sink no-human-ai-no_human-1d7edf4/tests/test_setup_mode_boot.py :302
assert "ANTHROPIC_AUTH_TOKEN" not in __import__("os").environ - dynamic code execution eval()/exec() no-human-ai-no_human-1d7edf4/tests/test_verifiers_gate.py :620
floored = eval(code, { # noqa: S307 - trusted source, own repo file - suspicious endpoint us-assets.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/src/no_human/api/app.py :461
_POSTHOG_SCRIPT_HOST = "https://us-assets.i.posthog.com" - suspicious endpoint us.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/src/no_human/api/app.py :462
_POSTHOG_CONNECT_HOSTS = "https://us.i.posthog.com https://us-assets.i.posthog.com" - suspicious endpoint us.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/src/no_human/config.py :2425
"posthog_host": "https://us.i.posthog.com", - suspicious endpoint 8.8.8.8 no-human-ai-no_human-1d7edf4/tests/test_coder_backend_settings.py :190
{"backend": "local", "local_base_url": "http://8.8.8.8:8000", - suspicious endpoint 8.8.8.8 no-human-ai-no_human-1d7edf4/tests/test_config.py :850
"http://8.8.8.8:8000", - suspicious endpoint 1.1.1.1 no-human-ai-no_human-1d7edf4/tests/test_config.py :851
"http://1.1.1.1", - suspicious endpoint 169.254.169.254 (cloud metadata) no-human-ai-no_human-1d7edf4/tests/test_config.py :862
"http://169.254.169.254", - suspicious endpoint us.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/tests/test_egress_allowlist.py :813
"https://us.i.posthog.com/batch/ (telemetry.posthog_host), or " - suspicious endpoint 8.8.8.8 no-human-ai-no_human-1d7edf4/tests/test_local_backend.py :178
{"local_model": "m", "local_base_url": "http://8.8.8.8"}, # public IP - suspicious endpoint us-assets.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/tests/test_telemetry.py :348
"script-src 'self' https://us-assets.i.posthog.com; " - suspicious endpoint us.i.posthog.com (telemetry) no-human-ai-no_human-1d7edf4/tests/test_telemetry.py :352
"https://us.i.posthog.com https://us-assets.i.posthog.com; " - committed secret Anthropic key no-human-ai-no_human-1d7edf4/desktop/mainIpc.test.mjs :146
sk-ant…(32 chars, redacted) - committed secret Anthropic key no-human-ai-no_human-1d7edf4/tests/test_adoption_harness.py :235
sk-ant…(33 chars, redacted) - committed secret Anthropic key no-human-ai-no_human-1d7edf4/tests/test_init.py :441
sk-ant…(34 chars, redacted)
[](https://mcpobservatory.com/servers/github:no-human-ai/no_human/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 no-human-ai.