SKILLEMALL.ai
GitHub ↗ RU Sign in

DD openresearch-cli

Use the `orx` CLI to run local OpenResearch projects from a terminal — create experiment branches, launch and supervise compute, inspect logs and evidence, and manage the experiment tree. Read this before driving `orx` programmatically.

Not recommendedcritical or high security findings · low grade D
alphaXiv/OpenResearch Agent Skills author: alphaXiv MIT 80 files · 43 scripts body ≈ 2 533 tokens Open the sourcegithub.com↗ analyzed 32 h ago

Use the orx CLI to run local OpenResearch projects from a terminal — create experiment branches, launch and supervise compute, inspect logs and evidence, and…

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

IntegrationLaTeXSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
66/100
safety, quality, tests
Safety 60%
54
Quality 40%
84
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.
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 · 9

  • high Dangerous commands cmd-pipe-to-shell .github/workflows/release.yml:184
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
Medium and low: 8
  • medium Dangerous commands cmd-pipe-to-shell-known-host demo/nanochat/base/runs/miniseries.sh:15
    Pipe-to-shell installer from a well-known host (still executes remote code)
    command -v uv &> /dev/null || curl -LsSf https://astral.sh/uv/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host demo/nanochat/base/runs/runcpu.sh:16
    Pipe-to-shell installer from a well-known host (still executes remote code)
    command -v uv &> /dev/null || curl -LsSf https://astral.sh/uv/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host demo/nanochat/base/runs/speedrun.sh:22
    Pipe-to-shell installer from a well-known host (still executes remote code)
    command -v uv &> /dev/null || curl -LsSf https://astral.sh/uv/install.sh | sh
  • medium Dangerous commands cmd-execpolicy-bypass demo/nanochat/experiment/runs/runcpu.sh:22
    Runs PowerShell with execution policy bypassed
    powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://astral.sh/uv/install.ps1 | iex" ;;
  • medium Dangerous commands cmd-pipe-to-shell-known-host demo/nanochat/experiment/runs/runcpu.sh:24
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -LsSf https://astral.sh/uv/install.sh | sh ;;
  • low Dangerous commands cmd-pipe-to-shell-known-host .github/workflows/release.yml:95
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.32.0/cargo-dist-installer.sh | sh"
    code literal
  • low Secrets in code secret-high-entropy-token Cargo.toml:89
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    windows-sys = { version = "0.61", features = ["Win3…ion", "Win3…ity", "Win3…als", "Win3…tem", "Win3…elp", "Win3…bje
    quoted
  • low Dangerous commands cmd-privilege demo/nanochat/base/nanochat/execution.py:62
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "setuid", "fork", "forkpty", "killpg", "rename", "renames", "truncate",
    code literal

Files scanned: 77. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Consistency. Frontmatter name (openresearch-cli) differs from the folder (OpenResearch)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
  • 100Steps. 20 steps
  • 100Execution cost. Instruction body is 2533 tokens
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (22 tags): a typed call is more reliable

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 236: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.