github Python analyzed 5898f68

PersonalJarvis/PersonalJarvis

Self-hosted voice assistant: speak to your computer — it answers aloud, types your dictation, and operates your apps.

maintainer: PersonalJarvis
license: MIT
first seen: 2026-07-28
last seen: 2026-08-02
releases · 30d: 20
short id

risk 66/100 · heuristic grade

D high

capability exposure inferred + 35
recent drift inferred + 20
tool safety inferred + 14
trust mitigators mixed − 3

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 3m ago · see ecosystem CVEs →

risk trajectory 1 movements

2d ago C · 51 → D · 66

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 2 findings · grade factor +14

high dangerous code

committed secret: Anthropic key · dynamic exec: __import__ sink, __import__()
low hidden prompt content

1 file(s) with hidden prompt content: PersonalJarvis-PersonalJarvis-5898f68/docs/plans/omni-latency-vision-v1/README.md (hidden-directive): "i18n-allow: product system prompt DE"

skills & danger signals github-tarball

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

analyzed commit 5898f68 · analyzer v28 · 2d ago

skills & prompt files 37

hidden: readme: hidden-directive (low) PersonalJarvis-PersonalJarvis-5898f68/docs/plans/omni-latency-vision-v1/README.md :100 i18n-allow: product system prompt DE
hidden: readme: hidden-directive (low) PersonalJarvis-PersonalJarvis-5898f68/docs/plans/omni-latency-vision-v1/README.md :100 i18n-allow: product system prompt DE

danger signals12

dynamic code execution __import__ sink PersonalJarvis-PersonalJarvis-5898f68/jarvis/missions/critic/runner.py :2066 __import__("os").unlink(schema_path)
dynamic code execution __import__() PersonalJarvis-PersonalJarvis-5898f68/jarvis/missions/workers/api_agent_worker.py :190 mod = __import__(mod_name, fromlist=[cls_name])
suspicious endpoint t.me PersonalJarvis-PersonalJarvis-5898f68/jarvis/channels/telegram.py :143 "enter the token from @BotFather (https://t.me/BotFather)."
suspicious endpoint t.me PersonalJarvis-PersonalJarvis-5898f68/jarvis/setup/wizard.py :348 help_url="https://t.me/BotFather",
suspicious endpoint api.telegram.org PersonalJarvis-PersonalJarvis-5898f68/jarvis/workflows/runner.py :457 url = f"https://api.telegram.org/bot{token}/sendMessage"
suspicious endpoint api.telegram.org PersonalJarvis-PersonalJarvis-5898f68/tests/unit/core/test_redact.py :96 f"POST https://api.telegram.org/bot{telegram_token}/getUpdates"
suspicious endpoint api.telegram.org PersonalJarvis-PersonalJarvis-5898f68/tests/unit/marketplace/test_connect_pat_schemes.py :69 _spec("telegram_path", "https://api.telegram.org/bot{token}/getMe").auth,
suspicious endpoint t.me PersonalJarvis-PersonalJarvis-5898f68/tests/unit/marketplace/test_telegram_connect.py :82 mode="pat_paste", token_creation_url="https://t.me/BotFather",
suspicious endpoint api.telegram.org PersonalJarvis-PersonalJarvis-5898f68/tests/unit/marketplace/test_telegram_connect.py :83 token_prefix="", validation_endpoint="https://api.telegram.org/bot{token}/getMe",
over-broad OAuth scope https://www.googleapis.com/auth/drive PersonalJarvis-PersonalJarvis-5898f68/tests/unit/marketplace/test_catalog_seed.py :187 assert spec.auth.scopes == ["https://www.googleapis.com/auth/drive"]
over-broad OAuth scope https://mail.google.com/ PersonalJarvis-PersonalJarvis-5898f68/tests/unit/marketplace/test_catalog_seed.py :203 assert "https://mail.google.com/" in spec.auth.scopes
committed secret Anthropic key PersonalJarvis-PersonalJarvis-5898f68/tests/missions/test_env.py :413 sk-ant…(37 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:PersonalJarvis/PersonalJarvis/badge.svg)](https://mcpobservatory.com/servers/github:PersonalJarvis/PersonalJarvis/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 PersonalJarvis.

PersonalJarvis/PersonalJarvis

skills & prompt files 37

danger signals12

Navigate

Stream

Features

Display