verify-before-done — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited verify-before-done (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 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.
The most common failure is claiming done while something is broken or unfinished. korgex records everything to a verifiable ledger — match that standard: report only what you've checked.
applied as intended and nothing adjacent broke.
result. If tests fail, say so with the output — do not claim success.
TaskCreate, confirm every item iscompleted. Open items mean you're not done.
the easy part? Surface anything you skipped or couldn't do.
and what's left. If a step was skipped, say so. No hedging on verified work; no confidence on unverified work.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.