The Simple Agent Development Kit.
- capability exposureinferred+22
- recent driftinferred+12
- tool safetyinferred+12
- trust mitigatorsmixed−5
inferredmixed
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 12m ago · see ecosystem CVEs →
- A · 0 → C · 41
no known CVEs for this server.
- highdangerous code
dynamic exec: __import__(), eval()/exec()
analyzed commit 3c8b9c3 · analyzer v17 · 2h ago
danger signals7
- dynamic code execution__import__()evilsocket-nerve-3c8b9c3/nerve/cli/create.py:59
module = __import__(f"nerve.tools.namespaces.{modname}", fromlist=[""]) - dynamic code executioneval()/exec()evilsocket-nerve-3c8b9c3/nerve/cli/eval.py:44
def eval( - dynamic code execution__import__()evilsocket-nerve-3c8b9c3/nerve/cli/namespaces.py:26
module = __import__(f"nerve.tools.namespaces.{modname}", fromlist=[""]) - dynamic code execution__import__()evilsocket-nerve-3c8b9c3/nerve/tools/compiler.py:75
module = __import__(f"nerve.tools.namespaces.{namespace}", fromlist=[""]) - dynamic code executioneval()/exec()evilsocket-nerve-3c8b9c3/nerve/tools/compiler.py:152
exec(func_body, func_namespace) - dynamic code executioneval()/exec()evilsocket-nerve-3c8b9c3/nerve/tools/mcp/compiler.py:136
exec(func_body, type_defs) - dynamic code executioneval()/exec()evilsocket-nerve-3c8b9c3/nerve/tools/namespaces/anytool.py:43
exec(code, func_namespace)
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:evilsocket/nerve/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 evilsocket.