create-github-action — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited create-github-action (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Follow the create-github-action skill workflow to scaffold a traditional deterministic GitHub Actions CI/CD workflow (no AI at runtime).
$ARGUMENTS — optional workflow type or purpose (e.g. test, build, deploy,lint, release, security). Omit to start with discovery.
$ARGUMENTS specifies a workflow type, use it to seed Phase 1 discoveryrequired secrets/environment variables, job steps, and caching strategy
.github/workflows/<name>.yml file.github/workflows/<name>.yml with complete job definitions, trigger events, permissions, and inline comments explaining each step.
$ARGUMENTS is empty: begin with workflow type discoverycreate-agentic-workflow~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.