Chrome MV3 浏览器调试黑盒：本地采集用户行为、网络、控制台等证据，并通过 MCP 供 AI Agent 查询。Local-first Chrome MV3 debugging black box for structured browser capture, export, and MCP-based AI agent analysis.
- capability exposure inferred + 28
- recent drift inferred + 12
- tool safety inferred + 5
inferred
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 8m ago · see ecosystem CVEs →
- B · 28 → C · 45
- B · 24 → B · 28
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()
analyzed commit 2aaeec9 · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules TuTouPower-capture_all-2aaeec9/AGENTS.md
danger signals2
- dynamic code execution eval() TuTouPower-capture_all-2aaeec9/tests/unit/websocket_capture_injected_script.test.ts :60
eval(PAGE_SCRIPT); - suspicious endpoint 93.184.216.34 TuTouPower-capture_all-2aaeec9/tests/unit/network_capture.test.ts :766
expect(is_self_origin_url('http://93.184.216.34/')).toBe(false);
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:TuTouPower/capture_all/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 TuTouPower.