ahstn/oceans-llm / actions/review-agent/skills/code-review
code-review
VerifiedReview GitHub pull requests across correctness, maintainability, architecture, security, and performance, with verified findings submitted as GitHub comments.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.3 KB |
| agents/openai.yaml | config | 43 B |
| references/axes/architecture.md | markdown | 1.8 KB |
| references/axes/correctness.md | markdown | 2.2 KB |
| references/axes/maintainability.md | markdown | 2.5 KB |
| references/axes/performance.md | markdown | 1.2 KB |
| references/axes/security.md | markdown | 1.6 KB |
| references/behaviour-communication.md | markdown | 2.9 KB |
| references/dead-code-and-simplifying.md | markdown | 1.2 KB |
| references/github-review.md | markdown | 2.5 KB |
| references/synthesis-decisions.md | markdown | 4.4 KB |
references/axes/security.md
View on GitHub# Security & Trust Boundaries Axis
Focus on untrusted data, identity, permissions, and exposure.
Look for:
- missing validation or unsafe parsing at trust boundaries
- missing authn/authz or tenant checks
- injection paths into SQL, shell, templates, files, or URLs
- secret exposure in code, logs, telemetry, or errors
- unsafe deserialization, path traversal, SSRF, or XSS-style flows where relevant
Report issues with a concrete path to unauthorized access, disclosure, or a privileged effect. A code-level trace is sufficient; actual exploitation or observed leakage is not required. Broad permissions alone are insufficient.
## Source, boundary, sink, and mitigation
For each candidate, show attacker control, the protected boundary, the vulnerable operation or missing guard, and concrete impact. Follow middleware, validators, ownership checks, parameterization, escaping, allowlists, signatures, and filesystem containment through the effective path. A dangerous API or missing nearby check is only a lead.
For CI, trace PR-controlled code, expressions, artifacts, caches, and dependencies into tokens, secrets, privileged runners, releases, or deployments. Verify which revision supplies workflow code and local actions. A broad permission or mutable ref alone is not enough; show the path to a privileged effect.
Check actual framework behavior before alleging injection, XSS, SSRF, or unsafe deserialization. Distinguish real exposed credentials from test placeholders. Generated code, scripts, and migrations still require review when executed with sensitive access. Do not propose guards for values that a verified boundary already excludes.
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 |