Is automatic-code-review safe to install?

SaferSkills independently audited automatic-code-review (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.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/automatic-code-review/SKILL.md · 1 file

skills/automatic-code-review/SKILL.md1.6 KB · Markdown

name: automatic-code-review

version: 1.0.0

description: "Automatic semantic code review triggered after file modifications. Hook-driven skill that logs file changes via PostToolUse and runs the automatic-code-reviewer agent on Stop. Not user-invocable — triggered automatically by lifecycle hooks."

user-invocable: false

disable-model-invocation: true

Automatic Code Review

Hook-driven skill that performs semantic code review after Claude finishes modifying files.

How It Works

PostToolUse hook — Logs every Write, Edit, or MultiEdit operation to /tmp/event-log-{SESSION_ID}.jsonl
Stop hook — Checks for new file modifications since the last review, then triggers the automatic-code-reviewer agent
Agent — Reads project-specific rules from the configured rulesFile and reviews only the changed files

Configuration

Settings in .claude/settings.json:

{
    "automaticCodeReview": {
        "enabled": true,
        "fileExtensions": ["ts", "tsx"],
        "rulesFile": ".claude/automatic-code-review/rules.md"
    }
}

Set "enabled": false to disable for a project.

Components

../../agents/automatic-code-reviewer.md — Review agent (model: haiku, tools: Read, Grep, Glob) — lives at plugin root agents/
../../hooks/hooks.json — Hook manifest (PostToolUse + Stop) — merged into plugin root hooks/
../../scripts/automatic-code-review-plugin.sh — Shell script for logging and review triggering — lives at plugin root scripts/
default-rules.md — Default semantic review rules (stays with skill)

automatic-code-review— agent skill

Is automatic-code-review safe to install?

Automatic Code Review

How It Works

Configuration

Components

Audit the pieces. Scan the whole. Decide.