Question 1

How does SkillzBench security-scan an agent skill?

Accepted Answer

Every skill is pinned to a commit SHA, then validated, license-checked, security-scanned and quality-judged as part of the Verify pillar. Results feed into a 0-100 trust score built from security, quality, license, maintenance and community signals.

Question 2

Which AI agents and tools does SkillzBench support?

Accepted Answer

SkillzBench focuses on agent skills — SKILL.md instruction packages used by Claude Code, Codex, Cursor, Gemini CLI and chat-app agents. Distribution and control happen through one MCP server plus per-agent loadouts.

Question 3

What about skills that contain scripts, not just instructions?

Accepted Answer

At launch, SkillzBench's full scanning and benchmarking scope covers instruction-only skills (SKILL.md plus text references). Script-bearing skills are listed link-out only, so you know exactly where the riskier territory begins.

Question 4

When can I start using SkillzBench?

Accepted Answer

SkillzBench is pre-launch and actively being built — the waitlist and newsletter are live now, and the product itself is not yet public. Joining the waitlist puts you first in line as the pillars roll out.

Question 5

How is this different from just reading a skill's README on GitHub?

Accepted Answer

A README tells you what the author claims. SkillzBench independently validates, license-checks and security-scans every version, benchmarks it in a sandbox against the same model with and without the skill, and publishes both a trust score and a separate Lift figure — with money never touching scores.

Agent Security Scanning for Freelancers