PPXANS-Harness
皮皮虾 (PPX Agent) 测试版 - 会自我修复、自我学习的超级 Agent
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
chen6896qqwee
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
ppx.chat.send发送消息给皮皮虾 agent, 返回完整回复。内部会执行完整工具调用循环 (记忆/搜索/命令等)。sessionId 用于区分会话上下文, 默认 default。
ppx.chat.stream发送消息给皮皮虾 agent, 流式返回回复 (SSE 进度通知)。内部会执行完整工具调用循环。sessionId 用于区分会话上下文, 默认 default。
ppx.sessions.list列出全部会话 (key/count/lastTs/title)。等价于旧 REST /sessions。
ppx.sessions.history读取指定会话的消息历史 (role/content 数组)。等价于旧 REST /sessions/:key/history。
ppx.sessions.rename重命名会话 (复制事件到新 key 并删旧 key)。
ppx.sessions.delete删除指定会话及其历史。
ppx.session.reset清空会话历史 (等同新建)。
ppx.providers.list列出全部 LLM 提供方 (key 已抹掉, 只留 api_key_set 标志)。等价于旧 REST /api/providers。
ppx.providers.add新增一个 LLM 提供方 (http 后端, 需 base_url + 模型 + key/env)。热重载立即生效。
ppx.providers.update更新指定提供方字段 (patch)。热重载立即生效。
ppx.providers.delete删除指定提供方。热重载立即生效。
ppx.providers.test健康探测指定提供方 (复用 agent 客户端, 无真实网络时返回可读结果)。
ppx.providers.reorder按给定 id 顺序重排提供方列表 (决定主模型优先级)。
ppx.settings.get读取可编辑设置 (用户名/HTTP 端口/安全/agent 预设)。敏感字段只回 set 标志。
ppx.settings.update更新设置 (patch: {user?, http?, security?, agent?, mcp?, tools?})。热重载立即生效。
ppx.task.templates列出任务面板内置技能模板 (按技能预置步骤), 供新建任务时选用。含 agent 训练评估/会话重命名/提示词方案/代码审查/MCP 合规/技能吸收。
ppx.task.create创建任务面板条目 (title/description/steps/template_id)。steps 为步骤标题数组, 每步初始 pending; 也可传 template_id 使用内置模板的步骤。
ppx.task.list列出全部任务 (含每步状态)。等价于任务面板读操作。
ppx.task.update更新任务状态或字段: {id, status?} status 为 todo|running|done|failed。
ppx.task.step更新某任务某步骤: {id, index, status?, detail?} index 从 0 开始, status 为 pending|running|done|failed。
ppx.task.delete删除任务面板条目。
ppx.task.run把任务交给 agent 执行: 标 running → 调 agent.chat 处理任务描述 → 全部步骤标 done → 结果回填任务 result。返回 agent 回复。
FEISHU_APP_IDFEISHU_APP_SECRETFEISHU_VERIFY_TOKENPPX_AGENT_DATA_DIRPPX_AGENT_GLOBAL_DATA_DIRPPX_AML_AUTHPPX_AML_AUTH_VALUEPPX_AML_DATAPPX_AML_PORTPPX_AUTH_TOKENPPX_DATA_DIRPPX_PORTPPX_PROVIDERWECHAT_AGENT_IDWECHAT_CORP_IDWECHAT_CORP_SECRETWECHAT_ENCODING_AES_KEYWECHAT_WEBHOOK_TOKENTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
22/22 tools missing one or more hints — ppx.chat.send (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ppx.chat.stream (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ppx.sessions.list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +19 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Shell command execution
1 call in production code run through a shell (src/utils/winutf8.js:10)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Secrets not logged
1 secret value sent to log
Redact or omit secret values from log output.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/chen6896qqwee/ppxans-harness)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check