review-docs — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review-docs (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.
Does this make sense?
Agents don't ask questions. They read and act.
Question: Can an AI understand this without human help?
# What's this about?
## This does X| Check | Issue |
|---|---|
| No header | Can't find topic |
| Vague header | Can't understand |
| No summary | Can't trust |
Every codeblock needs:
// What it does
const x = doThing()| Check | Issue |
|---|---|
| No explanation | Can't use |
| Wrong language | Can't run |
| Outdated | Won't work |
# Examplenpm install vant
| Check | Issue |
|-------|-------|
| No examples | Can't try |
| Wrong command | Won't work |
| Partial | Confusing |
### 4. Structure
| Check | Issue |
|-------|-------|
| No steps | Can't follow |
| Wrong order | Confusing |
| Missing steps | Stuck |
---
## AI-First Test
Try explaining to another AI:
> "Read this doc and do the thing. Tell me what you'd need to know."
If they can't do it, fix the doc.
---
## Output
---
**Role**: Docs Reviewer
**Input**: Documentation
**Output**: AI-readable?~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.