SKILLEMALL.ai
RU Sign in

B translate-cli

End-user guide for running and configuring the `translate` CLI across text/stdin/file/glob inputs, provider selection, presets, custom prompt templates, and TOML settings. Use when users ask for command construction, config updates (`translate config`/`translate presets`), provider setup, dry-run validation, or troubleshooting translation behavior.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: atacan v0.2.0 9 files body ≈ 472 tokens open source ↗ analyzed 29 h ago
IntegrationWriting and documentstype 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
B
84/100
Overall score
Safety 60%
82
Quality 40%
88
Tests bonus
0

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.

Instruction override
If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Review the high-severity findings: each costs 18 safety points. If one is a false positive, allow the rule id under guard.allow in spec.yaml.
  2. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  3. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 1

  • high Instruction override en-fake-system-prompt references/flags-and-subcommands.md:43
    Fake system prompt injected into content
    - `--system-prompt <TEMPLATE|@FILE>`: system prompt override.

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Lint

✓ Lint: no remarks

Process maturity 53/100

  • 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
  • 100Tools and files. No external tools needed
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 472 tokens
  • 100Running it twice. No mutating operations

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 350: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 13 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

External checks

ClawHub: clean
This is a documentation-only guide for a translation CLI, with sensitive behaviors that are expected for translation workflows and user-controlled.
LLM: benign (high) · VirusTotal: benign · 28 May 2026