AGENT SKILL

x-review-security

Reviews code changes for compliance with selected security frameworks. Verifies sensitive data handling, audit trails, and access control patterns.

License 许可
MIT
最近更新
2026-10-27
Stars
★ 0
Forks
1

01 前言 Front Matter

name
x-review-security
description
Reviews code changes for compliance with selected security frameworks. Verifies sensitive data handling, audit trails, and access control patterns.
allowed-tools
Read, Grep, Glob, Bash
argument-hint
[PR number or file paths]
fragment-slot
{ "slot": "review-specialist", "fragment-id": "security", "fragment-order": 10 }
user-invocable
true
requires-capabilities
[]

02 资源文件 1

03 SKILL.md 正文

Global Output Policy

  • Language: English ONLY.
  • Tone: Technical, Direct, and Concise.
  • Efficiency: Remove all conversational fillers and greetings to save tokens.

Skill: Security Compliance Review

Purpose

Review code changes against the compliance frameworks selected in the project configuration. Verify sensitive data handling, audit trails, access control patterns, and cryptography usage per active framework requirements.

Activation Condition

Include this skill when the project has compliance frameworks configured (PCI-DSS, LGPD, GDPR, HIPAA, SOX).

Triggers

  • /x-review-security 42 -- review PR #42 for security compliance
  • /x-review-security src/main/java/com/example/auth/ -- review specific file paths
  • /x-review-security -- review all current changes

Parameters

Parameter Type Required Default Description
target String No (current changes) PR number or file paths to review

Knowledge Pack References

Pack Files Purpose
security skills/security/references/security-principles.md Data classification, input validation, fail-secure patterns
security skills/security/references/application-security.md OWASP Top 10, security headers, secrets management
security skills/security/references/cryptography.md TLS, hashing, key management
compliance skills/compliance/SKILL.md and skills/compliance/references/ Active framework requirements

Workflow

Step 1 — Identify Active Frameworks

Read skills/compliance/references/ to identify active frameworks (PCI-DSS, LGPD, GDPR, HIPAA, SOX).

Step 2 — Verify Framework-Specific Requirements

For each active framework, verify the change against framework-specific requirements.

Step 3 — Check Sensitive Data Handling

Check data classification, masking, and encryption per skills/security/references/cryptography.md.

Step 4 — Verify Audit Trail Requirements

Ensure audit trail requirements are met for the active frameworks.

Step 5 — Check Access Control Patterns

Verify access control patterns comply with framework requirements.

Step 6 — Produce Compliance Report

Generate the compliance review report with per-framework results.

Output Format

## Compliance Review — [Change Description]

### Active Frameworks: [list]

### Per-Framework Results

#### [Framework Name]
- [x] Requirement met / [ ] Gap identified
- Finding: [description + remediation]

### Overall Verdict: COMPLIANT / NON-COMPLIANT / NEEDS REVIEW

Error Handling

Scenario Action
No compliance frameworks configured Report INFO: no frameworks active, skip review
Compliance KP files missing Warn and proceed with generic security review
PR number invalid or inaccessible Report error with PR number and suggest checking access

04 同仓库更多 Skills

review-bench
review-bench/edercnj_ia-dev-environment

x-parallel-eval

Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-task-plan / x-story-plan, applies the parallelism-heuristics knowledge pack (hard / regen / soft categories + hotspot overrides), and emits a collision matrix + serialization recommendation in Markdown (default) or JSON.

★ 0
review-bench
review-bench/edercnj_ia-dev-environment

parallelism-heuristics

Canonical catalog of file-collision heuristics for parallel task, story, and epic execution. Defines the File Footprint block format, the three Conflict Categories (hard / regen / soft), a hotspot list of high-contention paths, and the degrade-with-warning policy. Consumed by x-task-plan, x-story-plan, x-epic-map, x-parallel-eval, and x-dev-*-implement.

★ 0
review-bench
review-bench/edercnj_ia-dev-environment

x-watch-pr-ci

Polls a PR's CI checks and Copilot review status, blocking until checks complete or timeout. Returns one of 8 stable exit codes (SUCCESS=0, CI_PENDING_PROCEED=10, CI_FAILED=20, TIMEOUT=30, PR_ALREADY_MERGED=40, NO_CI_CONFIGURED=50, PR_CLOSED=60, PR_NOT_FOUND=70). Writes a versioned state-file for session resume.

★ 0
review-bench
review-bench/edercnj_ia-dev-environment

x-validate-docs

Documentation freshness gate: validates 6 dimensions (readme, api-specs, grpc-proto, adr, skill-docs, system-architecture) against code changes in a PR. Stack-aware — only validates targets declared/auto-detected from ProjectConfig.documentation.targets. Returns exit non-zero on staleness; produces structured report.

★ 0
review-bench
review-bench/edercnj_ia-dev-environment

x-update-system-architecture

Incrementally updates docs/architecture/system.md after an epic completes. Appends new entries to the Decision Log (§11) using x-internal-write-report --append (dedup by ## ID: marker) and surgically inserts component/integration changes into sections 1-10 via Edit. Idempotent: re-running with the same epic produces a byte-identical system.md.

★ 0
review-bench
review-bench/edercnj_ia-dev-environment

x-update-architecture

Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.

★ 0