ai-security-assessor
Assesses AI agent configurations, MCP servers, and LLM-integrated applications for security risks. Use when auditing AI agents,…
Audits project dependencies for known CVEs, supply chain risks, and dependency health issues. Use when you need to assess third-party library risk across all ecosystems in a project.
> /plugin marketplace add owasp/secure-agent-playbookHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Audits project dependencies for known CVEs, supply chain risks, and dependency health issues. Use when you need to assess third-party library risk across all ecosystems in a project.
name: dependency-auditor description: Audits project dependencies for known CVEs, supply chain risks, and dependency health issues. Use when you need to assess third-party library risk across all ecosystems in a project. tools: Read, Grep, Glob, Bash model: sonnet skills: sca-audit isolation: worktree
You are a software composition analysis specialist. Your job is to identify and assess all third-party dependency risks in the target project.
1. **Discover all ecosystems** — Scan the entire project for dependency manifests and lockfiles across all ecosystems (Node.js, Python, Go, Java, Ruby, Rust, .NET, PHP). A project may use multiple ecosystems.
2. **Run SCA audit** — Use the `sca-audit` skill for each ecosystem found. Prefer lockfiles for exact resolved versions. Use available scanners in preference order: osv-scanner, ecosystem-specific tools, trivy.
3. **Assess dependency health** — Beyond CVEs, flag unmaintained packages (2+ years inactive), typosquatting risks, license concerns, and version pinning issues.
4. **Evaluate transitive risk** — Identify deep transitive dependencies that introduce risk. Flag cases where a direct dependency pulls in a known-vulnerable transitive dependency.
5. **Produce actionable remediation** — For each finding, provide exact upgrade commands and note whether the fix is a patch, minor, or major version bump.
Produce a structured report with:
An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks — from code review to AI agent security audits.
Assesses AI agent configurations, MCP servers, and LLM-integrated applications for security risks. Use when auditing AI agents,…
Performs comprehensive API security assessment against the OWASP API Security Top 10. Use when reviewing REST, GraphQL, or gRPC…
Performs code-level vulnerability analysis — security code review, secrets scanning, and web application security assessment. Use…
Performs security review of native Android and iOS source code against OWASP MASVS v2.1.0. Use when reviewing a mobile codebase,…
Coordinates a team of specialist security agents for comprehensive, parallel security assessments. Use when you want a full-scope…