SKILLEMALL.ai
GitHub ↗ RU Sign in

AD skill-sandbox

Test untrusted skills in an isolated environment before installing. Monitors network access, filesystem writes, environment variable reads, and subprocess calls. Run any skill safely without risking your agent's data or credentials.

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 744 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Test untrusted skills in an isolated environment before installing.

As a process D 49/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

GeneratorInfrastructureData and analyticsAI 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
A
91/100
safety, quality, tests
Safety 60%
100
Quality 40%
78
Run on models
none yet
Process rating
D
49/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 0

✓ No critical or high findings

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")

Process rating: all ten parameters 49/100

  • 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. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (skill-sandbox) differs from the folder (arc-skill-sandbox)
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 27 steps
  • 100Execution cost. Instruction body is 744 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 232: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 27 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.