SKILLEMALL.ai
GitHub ↗ RU Sign in

BC magic-wormhole

Secure secret sharing for OpenClaw using magic-wormhole protocol

modbender/skill-library-mcp Agent Skills author: modbender MIT 10 files · 1 script body ≈ 3 765 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Secure secret sharing for OpenClaw using magic-wormhole protocol

As a process C 62/100 · Has gaps — weak spots: result and completion, running it twice

ProcedureGitHubSoftware developmenttype 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
B
85/100
safety, quality, tests
Safety 60%
84
Quality 40%
86
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands 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 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

    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 · 12

    ✓ No critical or high findings

    Medium and low: 12
    • medium Dangerous commands cmd-shell-rc install.sh:84
      Writes to a shell startup file
      echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
    • low Dangerous commands cmd-background-process docs/advanced-usage.md:270
      Starts a background / autostarted process (documentation of a security skill)
      sudo systemctl enable wormhole-server
      security skill
    • low Secrets in code secret-password-literal examples/agent-to-human.md:448
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      # "Database password: 8-br…gon"
      fixturequoted
    • low Secrets in code secret-password-literal examples/agent-to-human.md:465
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      # "New database password: 5-ca…ter"
      fixturequoted
    • low Secrets in code secret-password-literal examples/api-token-sharing.md:340
      Hard-coded password / key literal (may be an example) (placeholder value)
      # Save: PASSWORD=abc1…...
      placeholder
    • low Secrets in code secret-github-token examples/api-token-sharing.md:488
      GitHub token (placeholder value)
      ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
      placeholder
    • low Secrets in code secret-aws-key examples/api-token-sharing.md:498
      AWS access key ID (placeholder value)
      AKIA…PLE
      placeholder
    • low Dangerous commands cmd-shell-rc SKILL.md:135
      Writes to a shell startup file (documentation of a security skill)
      echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
      security skill

    A further 4 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 62/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 13 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 62 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3765 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
    • +3Description length 64: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • -220 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +4Structure: 59 headings
    • +3Step-by-step instructions: 62 items
    • +4Has examples (29 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.