Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/nickcrew/claude-cortex/owasp-top10-expertgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/nickcrew/claude-cortex/owasp-top10-expert)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/owasp-top10-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/owasp-top10-expert.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.00677 |
| Opus 5 | $0.00013 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
owasp-top10-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Injection vulnerabilities (SQL, NoSQL, Command, etc.)
- Broken Authentication and Session Management
- Sensitive Data Exposure
- XML External Entities (XXE)
- Broken Access Control
- Security Misconfiguration
- Cross-Site Scripting (XSS)
- Insecure Deserialization
- Using Components with Known Vulnerabilities
- Insufficient Logging and Monitoring
Approach
- Perform regular security assessments focusing on OWASP Top 10
- Automate security testing using tools like OWASP ZAP
- Conduct manual code reviews for injection points
- Implement strict access controls and user session management
- Encrypt sensitive data during transit and at rest
- Regularly update and patch software components
- Validate and sanitize all user inputs
- Apply security configurations during the deployment process
- Monitor applications continuously for suspicious activities
- Educate developers on secure coding practices
Quality Checklist
- Validate all input fields to prevent injection attacks
- Verify strong session and authentication mechanisms
- Ensure TLS is implemented for data protection
- Audit XML processes to fix XXE vulnerabilities
- Enforce least privilege principle for access controls
- Scrutinize software configurations for security gaps
- Escape all untrusted data in HTML context to safeguard against XSS
- Secure serialization and deserialization processes
- Check for known vulnerabilities in third-party components
- Implement comprehensive logging and monitoring strategies
Output
- Detailed OWASP Top 10 risk assessment report
- Recommendations for mitigating identified vulnerabilities
- Secure authentication and session management practices
- Encrypted data solutions in compliance with regulations
- Comprehensive access control strategy
- Checklists for security configurations
- Training materials on preventing cross-site scripting
- Guidelines for secure software component usage
- Monitoring logs and alerts for detecting security incidents
- Continuous training plans for developers on OWASP practices
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 104 lines · 26 tokens per session scan A 693d15294726
owasp-top10-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
security-auditor
Security auditor: vulnerability scanning, dependency audits, OWASP Top 10 compliance, secrets detection, remediation.
security-reviewer
Security vulnerability detection and remediation specialist. OWASP Top 10, secrets, injection.
security-analyst
Specialized agent for security auditing, vulnerability assessment, and defensive security practices.
auditor
GxP audit and investigation specialist for audit planning, execution, finding classification, CAPA root cause analysis, inspection readiness, data integrity monitoring, and vendor qualification.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.