Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
- capability exposure inferred + 26
- recent drift inferred + 20
- tool safety inferred + 5
inferred
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 1m ago · see ecosystem CVEs →
- D · 60 → C · 51
- C · 52 → D · 60
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit 278f41b · analyzer v28 · 2d ago
skills & prompt files 11
- skill balanced7-akashic-aurora-278f41b/.agents/skills/akashic-memory/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.agents/skills/plan-with-the-corpus/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.agents/skills/root-cause-before-fixes/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.agents/skills/verified-done/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.claude/skills/akashic-memory/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.claude/skills/plan-with-the-corpus/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.claude/skills/root-cause-before-fixes/SKILL.md
- skill balanced7-akashic-aurora-278f41b/.claude/skills/verified-done/SKILL.md
- agent-rules balanced7-akashic-aurora-278f41b/.cursor/rules/akashic-memory.mdc
- agent-rules balanced7-akashic-aurora-278f41b/AGENTS.md
- agent-rules balanced7-akashic-aurora-278f41b/research/in-flight/interiority-round-2/claude.md
danger signals4
- dynamic code execution eval()/exec() balanced7-akashic-aurora-278f41b/docs/_archive/pre-library/legacy/stack_manager/memory.py :123
total_rss += float(eval(mem_str) if "*" in mem_str else mem_str) - dynamic code execution eval()/exec() balanced7-akashic-aurora-278f41b/docs/_archive/pre-library/python_old/ai_setup_mcp.py :1175
exec(code, exec_globals) - dynamic code execution eval()/exec() balanced7-akashic-aurora-278f41b/docs/_archive/pre-library/python_old/gemma_voice_service.py :150
exec(code, exec_globals) - dynamic code execution eval()/exec() balanced7-akashic-aurora-278f41b/docs/_archive/pre-library/python_old/stack_manager.py :824
total_rss += float(eval(mem_str) if "*" in mem_str else mem_str)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:balanced7/akashic-aurora/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 balanced7.