Authenticated HTTPS attachment clients and PostgreSQL-backed service
- capability exposure inferred + 22
- tool safety inferred + 5
- trust mitigators mixed − 8
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 16h ago · see ecosystem CVEs →
- A · 14 → B · 19
- B · 19 → A · 14
- B · 24 → B · 19
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed v1.2.2 · analyzer v33 · 16h ago
skills & prompt files 1
- agent-rules package/AGENTS.md
danger signals2
- dynamic code execution new Function() package/dist/mcp/server.js :2895
const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); - suspicious endpoint 169.254.169.254 (cloud metadata) package/dist/serve/index.js :32257
Endpoint2["IPv4"] = "http://169.254.169.254";
[](https://mcpobservatory.com/servers/npm:@hasna/attachments/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 andreihasna2.