Rheinmir/review-safe
skills/review-safe/SKILL.md
Safe code audit — read-only review, no edits, findings only
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add Rheinmir/skills-kit review-safeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 9:37 PM10.2s1 file scanned
SKILL.md
- name:
- review-safe
- description:
- Safe code audit — read-only review, no edits, findings only
- allowed-tools:
- Read, Glob, Grep
Review target: $ARGUMENTS
Audit only. Do not fix. Do not edit.
Run these checks in parallel across target files:
- Security — SQL/cmd/XSS injection, auth bypass, hardcoded secrets, unsafe deserialization, missing input validation at system boundaries
- Logic — off-by-one, null/nil dereference, race conditions, silent error swallowing, wrong operator precedence
- Correctness — does implementation match intent? missing edge cases? assumptions that will break?
- Dependencies — unused imports, circular deps, unpinned versions in security-sensitive libs
Format each finding:
[CRITICAL|HIGH|MEDIUM|LOW] file:line
Issue: <one line — what is wrong>
Why: <why this matters — exploit path or failure mode>
Fix: <direction, not code>
Rules:
- No praise, no summary, no "overall the code looks..."
- Only findings that matter — skip style, skip nitpicks
- If $ARGUMENTS is a PR/diff: read changed lines first, then expand context only as needed
- MEDIUM and below: only report if actionable
Related Skills
Rheinmir/autopilot
development
VerifiedTrustedCommunity
Full autonomous execution from idea to working code
SKILL.mdUpdated Apr 16, 2026
Rheinmir/autopilot
development
VerifiedTrustedCommunity
Full autonomous execution from idea to working code
SKILL.mdUpdated Apr 16, 2026
Rheinmir/writer-memory
documentation
VerifiedTrustedCommunity
Agentic memory system for writers - track characters, relationships, scenes, and themes
SKILL.mdUpdated Apr 16, 2026
Rheinmir/visual-verdict
testing
VerifiedTrustedCommunity
Structured visual QA verdict for screenshot-to-reference comparisons
SKILL.mdUpdated Apr 16, 2026