aiskillstore/marketplace / skills/89jobrien/security-audit
security-audit
VerifiedSecurity auditing and vulnerability assessment specialist. Use when conducting security reviews, analyzing code for vulnerabilities, performing OWASP assessments, or creating security audit reports.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
| references/owasp-checklist.md | markdown | 3.0 KB |
| references/security-audit.template.md | markdown | 4.5 KB |
| skill-report.json | config | 11.1 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T13:33:22.087Z",
"slug": "89jobrien-security-audit",
"source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/security-audit",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "9ac8cbd733ad16bf7875e0e9ab2c0945ab26368bbe47b347523e130099e9f500",
"tree_hash": "b6944d6569015ffdbdb29a9680092939d2e05c4de74e6200c82989370cead6ae",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "security-audit",
"description": "Security auditing and vulnerability assessment specialist. Use when conducting security reviews, analyzing code for vulnerabilities, performing OWASP assessments, or creating security audit reports.",
"summary": "Run structured security audits with OWASP checks, CVSS context, and remediation planning.",
"icon": "📦",
"version": "1.0.2",
"author": "Joseph OBrien",
"license": "MIT",
"tags": [
"security-audit",
"vulnerability-assessment",
"owasp",
"cvss",
"remediation"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
],
"category": "security"
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All three static findings were adjudicated as false positives. The suspected template-injection line is an audit report placeholder, and the two shell-execution findings are Markdown file references. No semantic evidence of prompt injection, exfiltration, or malicious intent was found.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 39
}
]
}
],
"static_findings": [
{
"id": "blocker:references/security-audit.template.md:13:template-injection-targeting-system-prompt",
"category": "blocker",
"severity": "medium",
"pattern": "Template injection targeting system prompt",
"file": "references/security-audit.template.md",
"line_start": 13,
"line_end": 13,
"snippet": "**Target:** {{APPLICATION_OR_SYSTEM}}"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 38,
"snippet": "- `references/SECURITY_AUDIT.template.md` - Comprehensive security audit report format"
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "- `references/owasp_checklist.md` - OWASP Top 10 checklist with CVSS scoring and CWE references"
}
],
"finding_verdicts": [
{
"id": "blocker:references/security-audit.template.md:13:template-injection-targeting-system-prompt",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line is a report template placeholder identifying the audited application or system, not an instruction to alter system prompts. No override language or prompt-control text appears around it."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The snippet uses Markdown inline code to name a reference file. It does not invoke a Ruby backtick or shell command, and no executable command is present."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The snippet uses Markdown inline code to name a reference file. It does not invoke a Ruby backtick or shell command, and no executable command is present."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 3,
"total_lines": 437,
"audit_model": "codex",
"audited_at": "2026-07-05T13:33:22.087Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Audit Applications for Security Risk",
"value_statement": "Security reviews can miss common vulnerabilities when scope, severity, and remediation are unclear. This skill guides structured audits using OWASP checks, CVSS scoring, and report templates.",
"seo_keywords": [
"security audit skill",
"vulnerability assessment",
"OWASP Top 10",
"CVSS scoring",
"remediation planning",
"Claude",
"Codex",
"Claude Code",
"secure code review",
"dependency audit"
],
"actual_capabilities": [
"Guides security code reviews for application releases.",
"Maps findings to OWASP Top 10 categories.",
"Supports CVSS severity scoring and CWE classification.",
"Structures reports with executive summaries, scope, findings, and remediation.",
"Reviews authentication, authorization, data protection, and dependency risks."
],
"limitations": [
"Does not run automated scanners or commands by itself.",
"Requires access to relevant code, architecture, and configuration evidence.",
"Cannot validate exploitability without safe test environments and user approval.",
"Uses reference checklists, so final decisions need professional judgment."
],
"use_cases": [
{
"title": "Pre-Release Security Review",
"description": "Engineering teams use the skill to review code, dependencies, and controls before production release.",
"target_user": "Software engineering teams"
},
{
"title": "OWASP Gap Assessment",
"description": "Security teams compare an application against OWASP Top 10 categories and document missing controls.",
"target_user": "Security analysts"
},
{
"title": "Remediation Planning",
"description": "Product and platform leads turn findings into prioritized fixes with severity, impact, and owner-ready recommendations.",
"target_user": "Product and platform leaders"
}
],
"prompt_templates": [
{
"title": "Start a Basic Audit",
"scenario": "Beginner scope review",
"prompt": "Audit my application for security risks. Scope: [components]. Focus on OWASP Top 10 and summarize the highest risks first."
},
{
"title": "Review a Pull Request",
"scenario": "Focused code review",
"prompt": "Review this pull request for authentication, authorization, input validation, and secret handling issues. Provide severity, evidence, and remediation steps."
},
{
"title": "Create a Full Audit Report",
"scenario": "Structured assessment report",
"prompt": "Create a security audit report for [system] using the provided architecture, code notes, and dependency data. Include CVSS, CWE, OWASP mapping, and a remediation roadmap."
},
{
"title": "Adjudicate Scanner Results",
"scenario": "Advanced evidence review",
"prompt": "Adjudicate these scanner results against source evidence. Remove false positives, keep uncertain items with confidence, and produce an executive risk summary."
}
],
"output_examples": [
{
"input": "A web API needs a release security review.",
"output": [
"Executive summary with overall risk and severity counts.",
"Findings grouped by critical, high, medium, and low impact.",
"Remediation roadmap with owner-ready next steps."
]
},
{
"input": "A team has OWASP checklist notes for a customer portal.",
"output": "Gap assessment showing tested categories, available evidence, missing controls, and recommended follow-up reviews."
},
{
"input": "Scanner output contains many possible dependency issues.",
"output": "Prioritized list of validated package risks, likely false positives, upgrade guidance, and unresolved questions."
}
],
"best_practices": [
"Provide scope, architecture, code paths, and deployment context before asking for findings.",
"Ask for evidence, severity rationale, and remediation for every confirmed issue.",
"Review generated recommendations with the system owner before publishing an audit report."
],
"anti_patterns": [
"Using the skill as a replacement for authorized penetration testing.",
"Requesting exploit steps without a controlled and approved test environment.",
"Publishing severity ratings without validating business impact and asset exposure."
],
"faq": [
{
"question": "What standards does it use?",
"answer": "It references OWASP Top 10 categories, CVSS severity ranges, and common CWE identifiers."
},
{
"question": "Can it run scanners?",
"answer": "No. It provides audit guidance and report structure. Users must run approved tools separately."
},
{
"question": "Does it handle dependency reviews?",
"answer": "Yes. It includes dependency vulnerability assessment and remediation planning in its workflow."
},
{
"question": "Can it produce executive summaries?",
"answer": "Yes. The report template includes severity counts, key findings, scope, and overall risk."
},
{
"question": "Is it suitable for compliance work?",
"answer": "It can support evidence collection and structured review, but compliance sign-off needs qualified reviewers."
},
{
"question": "Which tools support it?",
"answer": "The skill declares support for Claude, Codex, and Claude Code."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "owasp-checklist.md",
"type": "file",
"path": "references/owasp-checklist.md",
"lines": 116
},
{
"name": "security-audit.template.md",
"type": "file",
"path": "references/security-audit.template.md",
"lines": 262
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 59
}
]
}
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: 472k | 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: 472k | 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: 472k | 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 |