stabbur — the Norwegian storehouse for your models: build a local LLM library, then run, chat and serve it with MCP tools. Source-available, proprietary.
- capability exposure inferred + 35
- tool safety inferred + 7
- 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 1w ago · see ecosystem CVEs →
No known CVEs for this server.
- 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 61adba9 · analyzer v33 · 6d ago
skills & prompt files 1
- agent-rules winterop-com-stabbur-61adba9/CLAUDE.md
danger signals3
- suspicious endpoint 93.184.216.34 winterop-com-stabbur-61adba9/tests/mcp_servers/http/test_http.py :75
target, headers, ext = app._pin_host(urlparse("https://93.184.216.34:8443/x?q=1")) - suspicious endpoint 169.254.169.254 (cloud metadata) winterop-com-stabbur-61adba9/tests/mcp_servers/web/test_web.py :46
"http://169.254.169.254/latest/meta-data/", - suspicious endpoint 93.184.216.34 winterop-com-stabbur-61adba9/tests/mcp_servers/web/test_web.py :54
app._guard_url("http://93.184.216.34/")
[](https://mcpobservatory.com/servers/github:winterop-com/stabbur/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 winterop-com.