mmaideveloper/aiarchitecttoolkit / skills/security-review
security-review
VerifiedReview a proposed or implemented solution for security risks, threat coverage, control effectiveness, and security evidence. Use for focused architecture security reviews, threat-informed release checks, or security findings; do not use as penetration testing or as proof of compliance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
| agents/openai.yaml | config | 210 B |
| references/security-review-method.md | markdown | 1.2 KB |
references/security-review-method.md
View on GitHub# Security Review Method
Use this evidence matrix:
| Asset or boundary | Threat scenario | Expected control | Evidence | Effectiveness | Finding/action |
|---|---|---|---|---|---|
| <asset/boundary> | <credible attacker action> | <requirement/control> | <artifact, file:line, configuration, test, or runtime evidence> | Effective / Partial / Ineffective / Not verified / Not applicable | <risk and action> |
Rate findings using likelihood and impact in the project-defined risk model. If none exists, use:
- `Critical`: credible path to catastrophic safety, confidentiality, integrity, availability, tenant-isolation, or irreversible-data impact; stop release.
- `High`: exploitable or likely material impact with inadequate prevention or detection; resolve before release unless an authorized exception exists.
- `Medium`: meaningful defense-in-depth, monitoring, recovery, or hardening gap.
- `Low`: limited exposure or security-maintainability weakness.
For every finding include: identifier, severity, affected scope, scenario, evidence, impact, likelihood rationale, remediation, verification method, owner if known, and related architecture requirement or decision. Record uncertainty instead of inflating confidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |