LeanCTX — Context Intelligence for AI systems.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- 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 3d ago · see ecosystem CVEs →
- D · 79 → D · 64
- C · 53 → D · 79
- D · 79 → C · 53
- C · 48 → D · 79
- D · 79 → C · 48
- C · 48 → D · 79
- D · 72 → C · 48
- D · 60 → D · 72
- D · 72 → D · 60
- D · 66 → D · 72
- C · 36 → D · 66
- D · 66 → C · 36
- D · 79 → D · 66
- C · 40 → D · 79
No known CVEs for this server.
- high dangerous code
committed secret: GitHub token, OpenAI key, Anthropic key · dynamic exec: vm exec
analyzed v3.9.12 · analyzer v33 · 3w ago
skills & prompt files 13
- agent-rules yvgude-lean-ctx-8c9c8dd/.clinerules
- agent-rules yvgude-lean-ctx-8c9c8dd/.cursor/rules/compression-safety.mdc
- agent-rules yvgude-lean-ctx-8c9c8dd/.github/copilot-instructions.md
- agent-rules yvgude-lean-ctx-8c9c8dd/.windsurfrules
- agent-rules yvgude-lean-ctx-8c9c8dd/AGENTS.md
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/.clinerules
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/AGENTS.md
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/CLAUDE.md
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/examples/.windsurfrules
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/examples/CLAUDE.md
- agent-rules yvgude-lean-ctx-8c9c8dd/rust/src/templates/CLAUDE.md
- skill yvgude-lean-ctx-8c9c8dd/rust/src/templates/SKILL.md
- skill yvgude-lean-ctx-8c9c8dd/skills/lean-ctx/SKILL.md
danger signals8
- dynamic code execution vm exec yvgude-lean-ctx-8c9c8dd/rust/src/dashboard/static/tests/cockpit-commander.test.js :28
vm.runInNewContext(source, context, { filename: componentPath }); - dynamic code execution vm exec yvgude-lean-ctx-8c9c8dd/rust/src/dashboard/static/tests/cockpit-context.test.js :26
vm.runInNewContext(source, context, { filename: componentPath }); - dynamic code execution vm exec yvgude-lean-ctx-8c9c8dd/rust/src/dashboard/static/tests/cockpit-overview.test.js :26
vm.runInNewContext(source, context, { filename: componentPath }); - committed secret GitHub token yvgude-lean-ctx-8c9c8dd/rust/src/core/addons/runtime.rs :49
ghp_01…(42 chars, redacted) - committed secret OpenAI key yvgude-lean-ctx-8c9c8dd/rust/src/core/policy/coverage.rs :55
sk-sup…(23 chars, redacted) - committed secret Anthropic key yvgude-lean-ctx-8c9c8dd/rust/src/core/secret_detection.rs :303
sk-ant…(33 chars, redacted) - committed secret OpenAI key yvgude-lean-ctx-8c9c8dd/rust/tests/compliance_frameworks.rs :220
sk-sup…(23 chars, redacted) - committed secret GitHub token yvgude-lean-ctx-8c9c8dd/rust/tests/gateway_postprocess_e2e.rs :216
ghp_01…(42 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:yvgude/lean-ctx/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 yvgude.