Code Review Security
Run security-focused code review when changes cross trust boundaries or may affect authentication, authorization, input validation, secrets handling, or sensitive-data exposure. Use for merge decisions requiring explicit security findings; do not use for non-security-only review scope.
Install
$ agentstack add skill-kentoshimizu-sw-agent-skills-code-review-security ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-kentoshimizu-sw-agent-skills-code-review-security) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Code Review Security
Overview
Use this skill to identify exploitable weaknesses and data-protection risks before merge.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Inputs To Gather
- Changed trust boundaries (external input, authn/authz, storage, outbound calls).
- Sensitive data categories and handling paths.
- Existing security controls (validation, encoding, policy checks, audit logs).
- Threat model assumptions relevant to the changed area.
Deliverables
- Security findings with exploit path and severity.
- Risk acceptance/escalation items for unresolved issues.
- Required remediation and verification actions.
Finding Focus Areas
- Input validation and injection paths.
- Authn/authz bypass and privilege escalation.
- Secret leakage in code, logs, or telemetry.
- Sensitive data exposure at rest/in transit/in logs.
- Unsafe defaults, fallback auth, or policy bypass paths.
Quick Example
- Diff adds debug log containing full JWT token.
- Finding: high-severity secret exposure risk.
- Fix direction: redact token, log token hash/metadata only.
Quality Standard
- Findings describe concrete exploit scenario, not vague concern.
- Severity reflects impact + exploitability.
- Fix guidance removes root cause and prevents recurrence.
- Residual risk is explicit when immediate full fix is infeasible.
Workflow
- Map changed code to trust boundaries and assets.
- Evaluate exploit paths across input, auth, and data handling.
- Verify security controls are present and correctly ordered.
- Identify regressions introduced by fallback or bypass logic.
- Publish prioritized findings and remediation requirements.
Failure Conditions
- Stop when high-severity vulnerabilities remain unresolved.
- Escalate when risk acceptance exceeds policy or lacks approver.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: KentoShimizu
- Source: KentoShimizu/sw-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.