CD claude-anywhere

不是聊天机器人，是你口袋里的AI员工。Claude Anywhere 让你通过 Telegram、企业微信、QQ 随时随地读写文件、执行命令、分析图片、管理代码。Not a chatbot — your AI engineer in your pocket. Claude Anywhere lets you read/write files, execute commands, analyze images, manage code — from Telegram, WeChat Work, or QQ, anywhere.

ClawHub Agent Skills author: yizhao1978 v1.6.2 MIT-0 15 files · 1 script body ≈ 453 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

Analyzer Telegram AI 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

73/100

safety, quality, tests

Safety 60%: 77
Quality 40%: 68
Run on models: none yet

Process rating

46/100

Unfinished process

Result and completion w 14: 0
Inputs and preconditions w 11: 0
Failures and branches w 10: 0

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

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 · 19

✓ No critical or high findings

Medium and low: 19

medium Dangerous commands cmd-privilege README.md:271

Privilege escalation / world-writable permissions
```
sudo cp systemd/claude-anywhere.service /etc/systemd/system/
```
low Exfiltration read-dotenv bridge-telegram.mjs:36

Reads a .env file (quoted — discussed, not commanded)
```
console.error("ERROR: TELEGRAM_BOT_TOKEN is not set. Copy .env.example to .env and fill in the token.");
```
quoted
low Exfiltration read-dotenv index.html:705

Reads a .env file
```
<code>cp .env.example .env</code><br>
```
low Exfiltration read-dotenv index.html:739

Reads a .env file
```
<code>cp .env.example .env</code><br>
```
low Exfiltration read-dotenv index.html:773

Reads a .env file
```
<code>cp .env.example .env</code><br>
```
low Exfiltration read-dotenv install.sh:7

Reads a .env file (quoted — discussed, not commanded)
```
echo "1. cp .env.example .env"
```
quoted
low Secrets in code secret-high-entropy-token package-lock.json:142

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…GBE+Xw7U+pHMY…0q5/TER/tYh3PQ==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:170

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…HxH+tv3k…kSo+8o0wxg9lZWw==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:186

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…9dM/mwVgvbZJaSNaRk+bshk…Kbz+IoId…W0Q=="
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:236

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…Wbq+zHns…i0d//cwIw…jdV+vww==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:245

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…dfW+r2Wn…xUV+azxA…TQk+2N2X…Rtg=="
```
detector

low Exfiltration read-dotenv README.md:30