create-issue-gate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited create-issue-gate (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
Use this issue-gating workflow only when the user or current project explicitly requires it. It is not a universal prerequisite for implementation or permission to create public issues.
Core rule: within an explicitly required issue gate, dependent execution requires valid acceptance criteria. Derive them from available authorized task context when possible; only indispensable unresolved decisions need clarification.
draft, ready, and blocked work before execution begins.Every issue must include these sections:
draft | ready | blocked | done)Acceptance criteria are valid only when they are testable and pass/fail checkable.
Examples:
If criteria are missing or non-testable:
Status: draftExecution Gate: blocked (missing valid acceptance criteria)Default to preparing the exact issue body for review. If issue creation is authorized, use the named repository and existing template; a skill invocation does not grant permission to post to an unrelated repository.
Use a body template like:
## Problem
<what is broken or missing>
## Goal
<what outcome is expected>
## Scope
- <in scope item>
## Non-Goals
- <out of scope item>
## Acceptance Criteria
- <explicit, testable criterion 1>
## Dependencies/Blockers
- <dependency or none>
## Status
draft|ready|blocked|done
## Execution Gate
allowed|blocked (<reason>)draft: missing/weak acceptance criteria or incomplete task definitionready: acceptance criteria are explicit and testableblocked: external dependency prevents progressdone: acceptance criteria verified with evidenceNever mark an issue ready without valid acceptance criteria.
Execution workflows (for example closed-loop-delivery) may start only when:
readyallowedIf an applicable required issue remains draft due to an indispensable missing decision, pause that dependent step and continue independent safe work. Do not ask again for criteria already clear in the user’s request.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.