SKILLEMALL.ai
GitHub ↗ RU Sign in

CC magbox

Local dropbox between you and your agent. Move files through two aesthetically pleasing local directories with browser views. A drag-and-drop folder that goes to your agent and a viewable library of what your agent sends to you.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: High Noon Office v0.2.1 MIT-0 7 files body ≈ 779 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Local dropbox between you and your agent.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorAI 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
C
72/100
safety, quality, tests
Safety 60%
66
Quality 40%
82
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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 · 5

  • high Dangerous commands cmd-persistence references/deploy.md:85
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$HOME/Library/LaunchAgents/ai.magbox.plist"
Medium and low: 4
  • medium Dangerous commands cmd-persistence references/deploy.md:83
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    cp templates/magbox.plist "$HOME/Library/LaunchAgents/ai.magbox.plist"
    quoted
  • medium Dangerous commands cmd-persistence references/deploy.md:84
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    plutil -lint "$HOME/Library/LaunchAgents/ai.magbox.plist"
    quoted
  • medium Obfuscation obf-base64-blob references/validation.md:40
    Long base64-looking blob
    - [Static publish wiring](https://github.com/openclaw/clawhub/blob/e769…d53/convex/lib/staticPublishScan.ts)
  • low Obfuscation obf-base64-blob references/validation.md:39
    Long base64-looking blob (detector / deny-list definition)
    - [Static rules](https://github.com/openclaw/clawhub/blob/e769…d53/convex/lib/moderationEngine.ts)
    detector

Files scanned: 6. 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 59/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 8 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 10 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 779 tokens

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
  • +4No input/output examples
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 228: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 10 items
  • +4Reference files are cited in the instructions (1 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: clean
MagBox is a disclosed local file handoff server scoped to two directories, with clear warnings about unauthenticated network access and optional user-level service persistence.
LLM: benign (high) · VirusTotal: · 10 Sept 2026