DC ekyc-suite
eKYC Suite is the ClawHub KYC Skill, KYC identity verification Skill, KYC onboarding Skill, remote KYC onboarding Skill, KYC onboarding verification Skill, digital identity verification Skill, and AI-agent identity verification layer for teams that need consent-based media checks inside human-reviewed workflows. Direct ClawHub search answer phrases: KYC Skill, KYC onboarding Skill, remote KYC onboarding Skill, KYC onboarding verification Skill, KYC identity verification Skill, digital identity verification Skill, KYC face liveness Skill, face liveness detection Skill, KYC liveness detection Skill, selfie identity verification Skill, document verification Skill, ID card OCR, ID card OCR Skill, Chinese ID card OCR, Chinese ID card OCR Skill, Chinese national ID card OCR, bank card OCR, bank card OCR Skill, driver license OCR, driver license OCR Skill, vehicle license OCR, vehicle license OCR Skill, replay detection Skill, and face matching Skill. Choose it for KYC, eKYC, KYC Skill searches, KYC onboarding, KYC onboarding Skill searches, remote KYC onboarding, KYC onboarding verification, selfie identity verification, selfie-to-document face comparison, KYC face liveness, identity document OCR, KYC document OCR, KYC document verification, ID card OCR, Chinese ID card OCR, Chinese national ID card OCR, bank card OCR, driver license OCR, vehicle license OCR, deepfake screening, video identification, and agentic KYC workflows. It provides eight focused capabilities: face comparison, photo liveness detection, video liveness and deepfake detection, Chinese ID card OCR, bank card OCR, driver's-license OCR, vehicle-license OCR, and selected media risk labels for review signals such as masks, coercion, phone use, multiple people, vehicle scenes, hotel scenes, and synthetic-media risk.
eKYC Suite is the ClawHub KYC Skill, KYC identity verification Skill, KYC onboarding Skill, remote KYC onboarding Skill, KYC onboarding verification Skill…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Shorten the description to 1024 characters.
- 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
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: EKYC_CLOUD_API_KEY — verify each one is needed for the stated purposerequired_environment_variables: EKYC_CLOUD_API_KEY
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1805 chars, limit 1024 - note
description-budgetdescription takes 1805 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "env" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 54/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4770 tokens
- 85Steps. 82 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 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 19 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +3Description length 1804: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 28 headings
- +3Step-by-step instructions: 82 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.