Configure your AI coding CLIs from one Git repo you can diff and revert: author AGENTS.md, MCP config, and Markdown memory once, render them to each tool's native format, check for drift, and sync across machines fail-closed. Linux stable, Windows beta.
- capability exposure inferred + 35
- recent drift inferred + 12
- 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.
graded 10m ago · see ecosystem CVEs →
- B · 32 → C · 49
- B · 19 → B · 32
- B · 22 → B · 19
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink
analyzed commit 1a7c05c · analyzer v28 · 13h ago
skills & prompt files 16
- prompt-file matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/council/prompts/brainstorm-continue.md
- prompt-file matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/council/prompts/brainstorm.md
- prompt-file matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/council/prompts/challenge.md
- prompt-file matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/council/prompts/code-review.md
- agent-rules matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/instructions/AGENTS.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/nexgen-update/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-close/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-council/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-doctor/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-groom/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-map/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-save/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/skills/vault-update/SKILL.md
- agent-rules matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/tests/fixtures/AGENTS.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/tests/fixtures/skills/fake-skill-a/SKILL.md
- skill matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/tests/fixtures/skills/fake-skill-excluded/SKILL.md
danger signals2
- dynamic code execution __import__ sink matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/agent-universal-layer/tests/test_council_seat_env_isolation.py :158
if hasattr(__import__("os"), "name") and __import__("os").name != "nt": - suspicious endpoint api.telegram.org matteopasseri407-NeXgen-Engine-1a7c05c/03-INFRA/scripts/agent_sync.py :2818
sent = _post_form(f"https://api.telegram.org/bot{token}/sendMessage", {"chat_id": chat, "text": msg})
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:matteopasseri407/NeXgen-Engine/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 matteopasseri407.