AgentSecOps

Manual SQL injection testing is slow and inconsistent. This skill provides structured SQLMap commands, authorization checks, validation steps, and reporting guidance for approved assessments.

Security skill authors need consistent workflows, references, and validation patterns. This template provides reusable structures for security guidance, rules, and CI scanning.

Web teams need a repeatable way to identify server weaknesses before attackers find them. This skill guides authorized Nikto scans and structured remediation reporting.

Hardcoded credentials can expose systems and fail compliance checks. This skill guides Gitleaks scans, configurations, hooks, CI pipelines, triage, and remediation.

Security teams need consistent visibility into vulnerable components, images, and infrastructure configuration. This skill provides practical Trivy workflows for assessment, reporting, and remediation.

Dependency vulnerabilities and license risks can reach production unnoticed. This skill guides Black Duck scans, policy gates, SBOM creation, and remediation triage.

Manual software inventories are incomplete and difficult to maintain. This skill guides repeatable Syft SBOM generation for containers, filesystems, archives, and CI pipelines.

Security flaws can remain hidden across large, multilingual repositories. This skill guides focused Semgrep scans, triage, custom rules, CI gates, and standards-aligned remediation.

Security flaws and exposed secrets can cross language boundaries and reach production. This skill guides Horusec scans, result triage, and CI integration.

Python security flaws can reach production unnoticed. This skill guides Bandit scans, prioritization, CI integration, and remediation with CWE and OWASP references.

Security scanner results are often fragmented across CI logs. This skill helps configure reviewdog to publish focused findings in pull requests and local hooks.

Manual network discovery can miss exposed services and inconsistent configurations. This skill provides structured Nmap workflows for authorized discovery, enumeration, vulnerability checks, and reporting.

Threat modeling often becomes outdated and disconnected from architecture changes. This skill helps create pytm models, STRIDE analysis, and diagram workflows for security reviews and CI.

Security teams need repeatable policy checks across clusters, infrastructure, and compliance controls. This skill guides Claude, Codex, and Claude Code through OPA Rego policy creation, testing, and CI/CD enforcement.

Security teams need structured review of authorized exploit validation, but these workflows carry high misuse risk. This skill documents Metasploit assessment steps with scope checks, logging, and cleanup guidance.

Network testers need clear netcat workflows for connectivity checks and controlled validation. This skill organizes netcat commands, authorization steps, and documentation guidance.

Endpoint investigations require consistent queries, collection plans, and evidence controls. This skill provides Velociraptor workflows, VQL patterns, and deployment templates for authorized response.

Infrastructure teams need consistent security checks before deployment. This skill guides Checkov scans, policy customization, suppression governance, compliance mapping, and CI integration.

Endpoint investigations often require many platform-specific tools and commands. This skill provides osquery workflows, detection queries, and packs for consistent forensic collection across major platforms.

SIEM-specific rules are difficult to reuse and maintain across platforms. This skill structures Sigma detections, conversions, ATT&CK mappings, and compliance coverage.

Security teams need repeatable runtime testing before releases. This skill guides authorized OWASP ZAP scans, authentication setup, API testing, and CI reporting.

Known vulnerabilities and misconfigurations can escape manual review. This skill guides authorized Nuclei scans, template selection, validation, and reporting.

Web fuzzing creates noisy results and legal exposure when scope, filters, and rate limits are unclear. This skill produces authorized ffuf workflows with focused discovery, filtering, output, and CI guidance.

Password audits need repeatable hash identification, attack selection, and reporting. This skill guides authorized Hashcat workflows for recovery, policy testing, and defensive remediation.