Local-first AI developer toolkit — knowledge base, code analysis, context management, and developer tools for LLM agents
- capability exposure inferred + 35
- tool safety inferred + 12
- supply-chain attested + 6
- trust mitigators mixed − 3
attested 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 · 41 → C · 50
- C · 53 → C · 41
- D · 68 → C · 53
- C · 56 → D · 68
- D · 65 → C · 56
- C · 59 → D · 65
No known CVEs for this server.
- high dangerous code
dynamic exec: new Function(), vm exec, eval()
analyzed v0.1.474 · analyzer v33 · 4w ago
danger signals5
- dynamic code execution new Function() package/scaffold/dist/definitions/bodies.mjs :497
- [ ] **eval/Function prevention**: No dynamic code execution from user input (\`eval()\`, \`new Function()\`, \`vm.runInNewContext()\`) - dynamic code execution vm exec package/scaffold/dist/definitions/bodies.mjs :497
- [ ] **eval/Function prevention**: No dynamic code execution from user input (\`eval()\`, \`new Function()\`, \`vm.runInNewContext()\`) - dynamic code execution eval() package/scaffold/dist/definitions/bodies.mjs :497
- [ ] **eval/Function prevention**: No dynamic code execution from user input (\`eval()\`, \`new Function()\`, \`vm.runInNewContext()\`) - dynamic code execution new Function() package/scaffold/dist/definitions/skills/typescript.mjs :353
- Avoid \`eval()\`, \`new Function()\`, and dynamic \`require()\`. - dynamic code execution eval() package/scaffold/dist/definitions/skills/typescript.mjs :353
- Avoid \`eval()\`, \`new Function()\`, and dynamic \`require()\`.
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/npm:@vpxa/aikit/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 anvpx.