Your AI agent runs skills it found on the internet. Do you know what they actually do?

SkillGrade runs behavioral safety tests on AI agent skills — prompt-injection traps, data-leak probes, should-refuse checks — and issues an A–F grade backed by traceable test runs. Registry scanners check code at publish time. We test behavior.

Flat pricing. No credits, no metered bills, no surprises — while the rest of AI tooling moves the other way.

Get early access How it works Free checks open to the public this month. Certification & monitoring available now for early customers.
ABCDF
How it works

Paste a skill. Get a verdict.

Submit

Paste a public skill URL or upload its SKILL.md. The skill runs inside our isolated test harness — never against your systems.

We test behavior

Versioned suites: prompt-injection traps hidden in content, credential-leak probes, should-refuse cases, core competency checks. Temperature 0, worst run counts.

Graded, traceably

A–F grade on a shareable page with suite version, timestamp, and run hash. Grades are generated only from test runs — there is no mechanism for us to hand-edit one.

What we test for

The failures scanners can't see

Prompt injection

Does the skill obey instructions hidden in the content it processes — fake "system notes," embedded commands, poisoned reviews?

Data leakage

Will it echo credentials, instructions, or private context it was exposed to? Will it contact addresses an attacker planted?

Refusal discipline

Does it decline what it must — unsupportable claims, destructive actions, out-of-scope requests — instead of guessing?

Competence

Does it actually do its job on realistic tickets, consistently, across repeated runs?

Pricing

Flat. No credits, no meters.

Payments are processed by Creem as merchant of record — VAT and sales tax handled automatically, worldwide.

Free Check

$0
  • 6-case behavioral mini-suite
  • A–F grade, shareable result page
  • Run hash + suite version shown
  • Rate-limited fair use

Certification

$79 one-time
  • Full suite, 3 consistency runs
  • Private detailed report
  • Signed attestation document
  • Embeddable "SkillGrade" badge

Monitoring

$29/mo per skill
  • Nightly re-certification runs
  • Regression alerts by email
  • Live public status page
  • Cancel anytime

Our honesty rules

1. No grade on this site is ever hand-entered. Reports are generated only from run artifacts, each carrying a content hash, suite version, and engine version.

2. We publish the worst run, not the best — and failures are listed, never suppressed.

3. A grade certifies tested behaviors at the time of the run. It is not a guarantee of future behavior, not a code audit, and not insurance. That's why monitoring exists.

4. Skill owners can dispute any grade: one click triggers a free re-run, and the outcome is published either way.

Questions
Who is SkillGrade for?

Anyone running AI agents with real access — businesses deploying OpenClaw or similar agent stacks, skill authors who want a trust mark, and teams choosing between skills. If your agent touches email, payments, publishing, or customer data, you want its skills graded.

Why should I trust your grades?

Because we designed away the ability to cheat: grades are generated exclusively from test runs (no admin override exists in our codebase), every public page shows the run hash and suite version, suites are versioned so numbers can't be quietly gamed, and disputes are resolved by public re-runs.

What happens when a certified skill changes?

Certification is point-in-time — the attestation says so explicitly. Monitoring re-runs the suite nightly and alerts you the moment behavior regresses, which is how a grade stays meaningful after model and skill updates.

Is my uploaded skill safe with you?

Skills run only inside an isolated test harness; we never execute skill code against live systems, never train on your content, and never share private reports. Uploads are capped and processed automatically.