SKILLEMALL.ai
GitHub ↗ RU Sign in

FF agent-handshake

通用 Agent 握手 — 自动发现、注册、打通任意服务器上的 AI Agent。服务器侧生成身份牌（自动识别 OpenCode/LangChain/CrewAI/通用FastAPI/MCP），本地侧持久化记忆，Cloudflare Tunnel 穿透 NAT。触发词：握手、连接 agent、发现 agent、快速握手、注册服务器、打通隧道、打洞、内网穿透。

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: lyliefeng v0.1.0 MIT-0 2 files body ≈ 2 407 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

通用 Agent 握手 — 自动发现、注册、打通任意服务器上的 AI Agent。服务器侧生成身份牌（自动识别 OpenCode/LangChain/CrewAI/通用FastAPI/MCP），本地侧持久化记忆，Cloudflare Tunnel 穿透 NAT。触发词：握手、连接 agent、发现…

As a process F 35/100 · Will not run — References files that are not bundled: references/servers/lvliefeng.json, references/servers/_index.json, references/servers/<hostname>.json

ProcedureCloudflareAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
37/100
safety, quality, tests
Safety 60%
23
Quality 40%
59
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/servers/lvliefeng.json, references/servers/_index.json, references/servers/<hostname>.json
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

  • high Exfiltration exfil-webhook-url SKILL.md:161
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    🌍 公网地址: https://random-name.trycloudflare.com
  • high Exfiltration exfil-webhook-url SKILL.md:165
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    handshake.sh https://random-name.trycloudflare.com "你的问题"
  • high Exfiltration exfil-webhook-url SKILL.md:175
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    bash scripts/accept.sh lvliefeng https://random-name.trycloudflare.com
  • high Exfiltration exfil-webhook-url SKILL.md:317
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    │  🔗 隧道: https://xxx.trycloudflare.com │
Medium and low: 1
  • medium Exfiltration exfil-webhook-url SKILL.md:145
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    服务器主动出站连接 Cloudflare（不需要开放入站端口），Cloudflare 分配一个 `https://xxx.trycloudflare.com` 公网地址。本地直接连这个地址，Cloudflare 转发到服务器。
    quoted

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/servers/lvliefeng.json
  • warning missing-ref reference to a missing file: references/servers/_index.json
  • warning missing-ref reference to a missing file: references/servers/<hostname>.json
  • warning missing-ref reference to a missing file: scripts/accept.sh
  • warning missing-ref reference to a missing file: scripts/discover.sh
  • warning missing-ref reference to a missing file: scripts/tunnel.sh
  • warning missing-ref reference to a missing file: scripts/config.sh
  • warning missing-ref reference to a missing file: scripts/handshake.sh
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/servers/lvliefeng.json, references/servers/_index.json, references/servers/<hostname>.json
  • 0Tools and files. 8 referenced file(s) missing: references/servers/lvliefeng.json, references/servers/_index.json, references/servers/<hostname>.json
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 15 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2407 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 180: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 15 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This skill is documented as an agent connection helper but also instructs users to deploy a persistent HTTP remote-command service with broad file and command access.
LLM: suspicious (high) · 19 Jul 2026