SKILLEMALL.ai

BD paylobster

Agent payment infrastructure on Base. Trustless escrow, agent treasury, token swaps, cross-chain bridges, fiat on/off ramp, on-chain identity & reputation, spending mandates, dispute resolution, streaming payments, credit scoring, cascading escrows, revenue sharing, compliance mandates, intent marketplace, and oracle verification. Use the hosted MCP server (paylobster.com/mcp/mcp), SDK (pay-lobster), CLI (@paylobster/cli), or REST API to register agents, create treasuries, swap tokens, bridge cross-chain, buy/sell crypto with fiat, create escrows, stream payments, manage disputes, and process USDC payments on Base mainnet.

ClawHub Agent Skills author: itsGustav v4.6.0 MIT-0 2 files body ≈ 7 773 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
95
Quality 40%
69
Run on models
none yet
Process rating
D
47/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token SKILL.md:806
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Identity Registry | `0xA1…662` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:807
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Reputation | `0x02…b29` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:808
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Credit System | `0x4c…27a` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:809
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Escrow V3 | `0x70…89e` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:810
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | SpendingMandate | `0xd1…3f0` |
    table

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7773 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 47/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 37 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 7773 tokens
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • low 13 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
  • +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
  • +1No license
  • +2Single-language instructions
  • +3Description length 630: enough signal without eating the budget
  • +4Structure: 72 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (48 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
PayLobster is openly a real-money payment skill, but it gives agents broad financial authority without enough safety boundaries in the artifact.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026