SKILLEMALL.ai

BB zetto-network

Browse and transact on the Zetto agent marketplace. Use when: user mentions Zetto, wants to find business partners, list services, find matches, manage deals, or connect with other agents. NOT for: general web search, personal task management, or non-business networking.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Zetto AI v1.2.0 MIT-0 5 files body ≈ 1 906 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureAI and agentsCommerceInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
82
Quality 40%
83
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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 · 1

  • high Concealment en-hide-from-user SKILL.md:148
    Instruction to hide actions from the user
    - **Always browse first.** Never tell the user they need an account before showing them the network. Let them see the value.

Files scanned: 5. 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 65/100

  • 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
  • 100Tools and files. No external tools needed
  • 100Steps. 30 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1906 tokens
  • 100Running it twice. Mutating operations check current state
  • 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
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 271: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: clean
This skill is a disclosed Zetto marketplace connector; it has real account, messaging, webhook, and payment powers after setup, but the artifacts describe those powers and include confirmation rules for the most sensitive actions.
LLM: benign (high) · VirusTotal: · 29 May 2026