confirm-gate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited confirm-gate (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Before touching anything, surface your interpretation. Output exactly this structure and stop:
Mode: [Plan / Build / Debug / Review - pick one]
I'm reading this as: [one sentence - what you think the actual task is, stripped of noise]
I'll touch:
I won't touch: [anything explicitly out of scope, or "nothing excluded" if full scope]
First step after confirmation: [the single next action]
Ambiguities: [anything unclear that would change the plan - or "none"]
Then stop. Do not proceed until the user responds.
If the user confirms ("yes", "go", "proceed", "looks right") - execute. If the user corrects anything - update your interpretation and confirm again before proceeding. If the user says "just do it" - execute but note what assumption you made.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.