A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
- capability exposure inferred + 35
- tool safety inferred + 5
- trust mitigators mixed − 5
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 →
- B · 32 → C · 35
- C · 44 → B · 32
- B · 32 → C · 44
- C · 44 → B · 32
- C · 51 → C · 44
- A · 0 → C · 51
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec(), __import__ sink, __import__()
- low dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
analyzed commit 22072fd · analyzer v33 · 2w ago
skills & prompt files 1
danger signals4
- dynamic code execution eval()/exec() agentscope-ai-agentscope-runtime-22072fd/src/agentscope_runtime/tools/mcp_wrapper.py :184
exec(code, namespace) - dynamic code execution __import__ sink agentscope-ai-agentscope-runtime-22072fd/tests/tools/test_agentscope_tool_adapter.py :284
"DASHSCOPE_API_KEY" not in __import__("os").environ, - dynamic code execution __import__() agentscope-ai-agentscope-runtime-22072fd/tests/unit/test_a2a_registry.py :365
return __import__(name, *args, **kwargs) - suspicious endpoint 1.2.3.4 agentscope-ai-agentscope-runtime-22072fd/tests/deploy/test_kruise_deployer.py :663
assert url == "http://1.2.3.4:9090"
[](https://mcpobservatory.com/servers/github:agentscope-ai/agentscope-runtime/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 agentscope-ai.