BB conto
Enforce fine-grained spending policies before executing any payment, transfer, swap, or bridge. Checks Conto policy engine for approval before money leaves your wallet. Use /conto to manage policies or check payments.
As a process B 68/100 · Nearly there — weak spots: result and completion, execution cost, running it twice
The same skill appears in 1 more place: ClawHub
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenREADME.md:169High-entropy token-like string (may be an id, hash or a credential)/conto check if a 10 pathUSD payment to 0x74…3a1 for API credits is allowed
-
low Secrets in code
secret-high-entropy-tokenREADME.md:177High-entropy token-like string (may be an id, hash or a credential)/conto check if a 500 pathUSD payment to 0x74…3a1 is allowed
-
low Secrets in code
secret-high-entropy-tokenREADME.md:193High-entropy token-like string (may be an id, hash or a credential)/conto check if a 10 pathUSD payment to 0x74…3a1 for gambling is allowed
-
low Secrets in code
secret-high-entropy-tokenREADME.md:201High-entropy token-like string (may be an id, hash or a credential)/conto check if a 600 pathUSD payment to 0x74…3a1 is allowed
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8434 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 40Execution cost. Instruction body is 8434 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 70 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +2Single-language instructions
- +3Description length 217: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (40 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
External checks
ClawHub: suspicious
The skill is mostly transparent about payment-policy management, but it can approve and execute real transfers, mutate policies, and store credentials, so it should be reviewed carefully before installation.
LLM: suspicious (high) · VirusTotal: · 16 Jul 2026