SKILLEMALL.ai
GitHub ↗ RU Sign in

FD ssh-deploy-skill

Universal SSH remote deployment tool - multi-server management, batch deployment, installation script templates with domestic mirror optimization. Supports remote installation of Git, Docker, MySQL, PostgreSQL, Nginx, Node.js, Redis, Python and more.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: awamwang v1.2.2 MIT-0 24 files · 10 scripts body ≈ 2 892 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

TemplateDockerPostgreSQLMySQLInfrastructuretype 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
35/100
safety, quality, tests
Safety 60%
12
Quality 40%
69
Run on models
none yet
Process rating
D
43/100
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

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.

Dangerous commands
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

  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.
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 · 26

  • high Exfiltration exfil-read-secret-files references/best-practices.md:71
    Reads credential / secret files
    cat ~/.ssh/id_rsa_new.pub | python3 scripts/deploy.py upload group:prod - ~/.ssh/authorized_keys
  • high Dangerous commands cmd-pipe-to-shell templates/install_nodejs.sh:20
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://rpm.nodesource.com/setup_${NODE_VERSION}.x | bash -
Medium and low: 24
  • medium Dangerous commands cmd-shell-rc references/mirrors.md:137
    Writes to a shell startup file
    echo 'export GOPROXY=https://goproxy.cn,direct' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc references/mirrors.md:204
    Writes to a shell startup file
    echo 'export HOMEBREW_BREW_GIT_REMOTE="https://mirrors.tuna.tsinghua.edu.cn/git/homebrew/brew.git"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc references/mirrors.md:205
    Writes to a shell startup file
    echo 'export HOMEBREW_CORE_GIT_REMOTE="https://mirrors.tuna.tsinghua.edu.cn/git/homebrew/homebrew-core.git"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc references/mirrors.md:206
    Writes to a shell startup file
    echo 'export HOMEBREW_BOTTLE_DOMAIN="https://mirrors.tuna.tsinghua.edu.cn/homebrew-bottles"' >> ~/.bashrc
  • medium Dangerous commands cmd-pipe-to-shell scripts/templates.py:373
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    curl -fsSL https://rpm.nodesource.com/setup_${NODE_VERSION}.x | bash -
    code literal
  • medium Dangerous commands cmd-pipe-to-shell-known-host templates/install_nodejs.sh:11
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_${NODE_VERSION}.x | bash -
  • medium Dangerous commands cmd-pipe-to-shell-known-host templates/install_nodejs.sh:29
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
  • low Dangerous commands cmd-background-process references/troubleshooting.md:70
    Starts a background / autostarted process
    systemctl start sshd && systemctl enable sshd
  • low Dangerous commands cmd-shell-rc scripts/templates.py:99
    Writes to a shell startup file (string literal in code, not executed)
    echo 'export GOPROXY=https://goproxy.cn,direct' >> ~/.bashrc
    code literal
  • low Dangerous commands cmd-background-process scripts/templates.py:203
    Starts a background / autostarted process (string literal in code, not executed)
    systemctl enable docker
    code literal
  • low Dangerous commands cmd-background-process scripts/templates.py:281
    Starts a background / autostarted process (string literal in code, not executed)
    systemctl enable mysqld
    code literal
  • low Dangerous commands cmd-background-process scripts/templates.py:312
    Starts a background / autostarted process (string literal in code, not executed)
    systemctl enable postgresql@$PG_VERSION-main
    code literal
  • low Dangerous commands cmd-background-process scripts/templates.py:327
    Starts a background / autostarted process (string literal in code, not executed)
    systemctl enable postgresql-$PG_VERSION
    code literal
  • low Dangerous commands cmd-background-process scripts/templates.py:349
    Starts a background / autostarted process (string literal in code, not executed)
    systemctl enable nginx 2>/dev/null || chkconfig nginx on
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/templates.py:369
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    curl -fsSL https://deb.nodesource.com/setup_${NODE_VERSION}.x | bash -
    code literal
  • low Dangerous commands cmd-background-process SKILL.md:423
    Starts a background / autostarted process
    systemctl enable xxx
  • low Dangerous commands cmd-background-process templates/install_docker.sh:44
    Starts a background / autostarted process
    systemctl enable docker
  • low Dangerous commands cmd-background-process templates/install_mysql.sh:32
    Starts a background / autostarted process
    systemctl enable mysql || update-rc.d mysql enable
  • low Dangerous commands cmd-background-process templates/install_mysql.sh:47
    Starts a background / autostarted process
    systemctl enable mysqld
  • low Dangerous commands cmd-background-process templates/install_nginx.sh:33
    Starts a background / autostarted process
    systemctl enable nginx 2>/dev/null || chkconfig nginx on || update-rc.d nginx enable
  • low Dangerous commands cmd-background-process templates/install_postgresql.sh:23
    Starts a background / autostarted process
    systemctl enable postgresql@$PG_VERSION-main
  • low Dangerous commands cmd-background-process templates/install_postgresql.sh:47
    Starts a background / autostarted process
    systemctl enable postgresql-${PG_VERSION}
  • low Dangerous commands cmd-background-process templates/install_redis.sh:19
    Starts a background / autostarted process
    systemctl enable redis 2>/dev/null || update-rc.d redis-server enable
  • low Dangerous commands cmd-background-process templates/install_redis.sh:24
    Starts a background / autostarted process
    systemctl enable redis

Files scanned: 24. 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")
  • note frontmatter-key unknown frontmatter key "when"
  • note frontmatter-key unknown frontmatter key "examples"

Process rating: all ten parameters 43/100

  • 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
  • 30Running it twice. 11 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2892 tokens
  • low 12 top-level sections: this looks like several domains in one skill

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
  • -220 emoji in the instructions: noise for the model
  • -32 of 5 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 250: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (19 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This appears to be a legitimate SSH deployment tool, but it needs Review because it can make broad remote server changes and automatically reads SSH configuration details without tight opt-in boundaries.
LLM: suspicious (high) · VirusTotal: · 29 May 2026