Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、VS Code 插件、桌面端、MCP 服务、RAG、Skills、SDD、浏览器自动化与 LoRA 规划模型
- capability exposureinferred+35
- tool safetyinferred+12
- trust mitigatorsmixed−3
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 14m ago · see ecosystem CVEs →
No known CVEs for this server.
- highexfiltration combofrontagent_run_task
single tool reads + sends: fs, net
analyzed commit f35f054 · analyzer v19 · 1d ago
skills & prompt files 20
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-cli/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-debugging/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-exploring/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-guide/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-impact-analysis/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.agents/skills/gitnexus/gitnexus-refactoring/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-cli/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-debugging/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-exploring/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-guide/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md
- agent-rulesFrontAgent-FrontAgent-f35f054/AGENTS.md
- agent-rulesFrontAgent-FrontAgent-f35f054/CLAUDE.md
- prompt-fileFrontAgent-FrontAgent-f35f054/models/frontagent-planner/prompts/error-recovery-prompt.md
- prompt-fileFrontAgent-FrontAgent-f35f054/models/frontagent-planner/prompts/planner-prompt.md
- skillFrontAgent-FrontAgent-f35f054/skills/frontend-design/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/skills/frontend-reviewer/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/skills/requirement-interviewer/SKILL.md
- skillFrontAgent-FrontAgent-f35f054/skills/skill-lifecycle/SKILL.md
[](https://mcpobservatory.com/servers/github:FrontAgent/FrontAgent/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 FrontAgent.