LibreControl — one universal /remote-control for every coding agent you run (Claude Code, Codex, Gemini, Cursor, Copilot, any MCP tool), across all your machines, centralized into the single chat app you choose: Telegram, WhatsApp, Slack, Signal, Discord. Self-hosted, with approvals and audit.
- capability exposure inferred + 35
- tool safety inferred + 5
- 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.
grade last moved 1w ago · see ecosystem CVEs →
- C · 49 → C · 37
- C · 57 → C · 49
- C · 49 → C · 57
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink
analyzed commit 6fdf091 · analyzer v33 · 2w ago
skills & prompt files 2
- agent-rules Pher217-LibreControl-6fdf091/AGENTS.md
- agent-rules Pher217-LibreControl-6fdf091/CLAUDE.md
danger signals11
- dynamic code execution __import__ sink Pher217-LibreControl-6fdf091/host-agent/agent_host/cli.py :70
cwd = args.cwd or __import__("os").path.expanduser("~") - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/observe/tests/test_delivery.py :772
"POST", "https://api.telegram.org/botX/sendMessage" - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/setup/telegram_flow.py :14
API_BASE = "https://api.telegram.org" - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/setup/tests/test_telegram_flow.py :101
message = f"GET https://api.telegram.org/bot{RAW_TOKEN}/getMe timed out" - suspicious endpoint t.me Pher217-LibreControl-6fdf091/backend/apps/setup/tests/test_telegram_flow.py :463
assert body["bot_link"] == "https://t.me/orcbot" - suspicious endpoint t.me Pher217-LibreControl-6fdf091/backend/apps/setup/views.py :133
"bot_link": f"https://t.me/{username}", - suspicious endpoint t.me Pher217-LibreControl-6fdf091/backend/apps/slash/handlers/sessions.py :97
return f"https://t.me/c/{abs_id}/{topic_id}" - suspicious endpoint t.me Pher217-LibreControl-6fdf091/backend/apps/slash/tests/test_sessions.py :273
assert "https://t.me/c/" in result - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/telegram/telegram_api.py :19
return f"https://api.telegram.org/bot{settings.TELEGRAM_BOT_TOKEN}" - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/telegram/tests/test_telegram.py :15
msg = "Client error for url 'https://api.telegram.org/bot123456:SECRETtoken/getUpdates'" - suspicious endpoint api.telegram.org Pher217-LibreControl-6fdf091/backend/apps/telegram/tests/test_telegram_api_429.py :50
monkeypatch.setattr(telegram_api, "_base_url", lambda: "https://api.telegram.org/botX")
[](https://mcpobservatory.com/servers/github:Pher217/LibreControl/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 Pher217.