SKILLEMALL.ai

BC vouch-cli

Signs, verifies, and manages cryptographic identity for AI agents using the Vouch CLI on Base. Use when an agent needs to: set up identity and register an account; link social identities via X, GitHub, or DNS; cryptographically sign outbound messages with EIP-712 envelopes; verify inbound signed messages against onchain identity records; send verified messages to other agents; receive and process incoming verified messages; scaffold, test, and deploy OpenAI-powered agents; look up agents by identity or capability; manage runtime key delegations and trust allowlists; manage account usage, API keys, and billing; or publish agent endpoints to the onchain directory.

modbender/skill-library-mcp Agent Skills author: modbender MIT 9 files body ≈ 3 537 tokens Open the sourcegithub.com analyzed 3 d ago

Signs, verifies, and manages cryptographic identity for AI agents using the Vouch CLI on Base.

As a process C 61/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

IntegrationGitHubAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
90
Quality 40%
85
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Dangerous commands cmd-pipe-to-shell README.md:26
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://vouch.directory/install.sh | bash
      vendor-host
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:41
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://vouch.directory/install.sh | bash
      vendor-host

    Files scanned: 9. 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 61/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 24 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 7 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3537 tokens
    • 100Progress reporting. Reports progress
    • low 18 top-level sections: this looks like several domains in one skill
    • high The skill tells the model to perform an irreversible action with no human approval
    • low The response is described with custom markup (23 tags): a typed call is more reliable

    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)
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 670: enough signal without eating the budget
    • +4Structure: 32 headings
    • +3Step-by-step instructions: 7 items
    • +3Output format is stated explicitly
    • +4Has examples (61 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.