create-agentic-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited create-agentic-workflow (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-agentic-workflow skill workflow to convert a local skill into a GitHub-native agentic workflow.
$1 — path to the existing skill directory to convert$2 — optional mode: ide (Copilot Chat slash command), cicd (autonomous quality gate),or both. Defaults to guided selection if omitted.
$1 provides a skill directory, resolve and validate the path; otherwise ask(Sequential / Orchestrator-Workers / Evaluator-Optimizer / Stateful), agent type, trigger events for CI/CD, and orchestration design for parallel patterns
scaffold_agentic_workflow.py with the gathered parametersgh aw compile, etc.)Generated GitHub workflow YAML and/or Copilot agent definition files, with implementation notes for the chosen agent type and pattern.
$ARGUMENTS is empty: begin with Phase 0 complexity gate, then guided discoveryconfigure each worker's permissions or use a PermissionRequest hook
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.