Agentic production system for Ableton Live 12 — 469 tools across 57 domains. Device atlas, user corpus, Splice intelligence, 9-band spectral perception, offline listening engine, Creative Director, semantic moves, and 12 creative engines.
- capability exposure inferred + 26
- recent drift inferred + 20
- tool safety inferred + 19
- 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 41s ago · see ecosystem CVEs →
- C · 47 → D · 62
- B · 23 → C · 47
- A · 0 → B · 23
No known CVEs for this server.
- high dangerous code
dynamic exec: unsafe yaml.load(), __import__()
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit ca9969b · analyzer v28 · 2d ago
skills & prompt files 18
- agent-rules dreamrec-LivePilot-ca9969b/AGENTS.md
- agent-rules dreamrec-LivePilot-ca9969b/CLAUDE.md
- agent-rules dreamrec-LivePilot-ca9969b/livepilot/agents/livepilot-producer/AGENT.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-arrangement/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-composition-engine/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-core/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-corpus-builder/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-creative-director/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-devices/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-evaluation/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-mix-engine/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-mixing/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-notes/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-performance-engine/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-release/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-sample-engine/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-sound-design-engine/SKILL.md
- skill dreamrec-LivePilot-ca9969b/livepilot/skills/livepilot-wonder/SKILL.md
danger signals3
- dynamic code execution unsafe yaml.load() dreamrec-LivePilot-ca9969b/mcp_server/atlas/overlays.py :357
parsed = yaml.load(f, Loader=_YAML_LOADER) - dynamic code execution __import__() dreamrec-LivePilot-ca9969b/tests/composer/develop/test_brief_builder.py :187
mod = __import__(f"mcp_server.composer.develop.{mod_info.name}", fromlist=[""]) - dynamic code execution __import__() dreamrec-LivePilot-ca9969b/tests/composer/full/test_no_form_templates.py :32
mod = __import__(mod_info.name, fromlist=[""])
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:dreamrec/LivePilot/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 dreamrec.