SKILLEMALL.ai
GitHub ↗ RU Sign in

BC windy-access

Wire any agent into the Windy ecosystem in one command. Use when the user wants their agent to have an email address (Windy Mail), a chat identity (Windy Chat), an Eternitas passport (verifiable identity), and free LLM access (Windy Mind, OpenAI-compatible). Auto-detects OpenClaw, Hermes Agent, Claude Code, and falls back to a generic ~/.windy/bundle.json for any other runtime. Triggers on phrases like 'connect my agent to Windy', 'give my agent an email', 'set up windy-connect', 'agent credentials bundle'. Pairing happens in a browser via Sign-in-with-Google.

ClawHub Hermes author: Grant Whitmer v0.3.1 MIT-0 3 files body ≈ 1 928 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
85
Quality 40%
74
Run on models
none yet
Process rating
C
64/100
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

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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-pipe-to-shell README.md:131
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    `curl get.windyconnect.com | sh`
    quoted
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(curl:*)
    allowed-tools: Read Bash(windy:*) Bash(pipx:*) Bash(curl:*) Bash(python3:*) AskUserQuestion
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:89
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://get.windyconnect.com | sh
    vendor-host

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 566 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 64/100

  • 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
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 12 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 3 branches, has a failure section
  • 100Execution cost. Instruction body is 1928 tokens
  • 100Running it twice. Mutating operations check current state

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
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +3Description length 566: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 12 items
  • +4Has examples (5 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
This skill is purpose-aligned, but it asks agents to install and run a third-party onboarding CLI that can write credentials across multiple runtimes, with an unsafe installer path and broad activation language.
LLM: suspicious (high) · VirusTotal: · 28 May 2026