ai-security-assessor
Assesses AI agent configurations, MCP servers, and LLM-integrated applications for security risks. Use when auditing AI agents,…
Performs security review of native Android and iOS source code against OWASP MASVS v2.1.0. Use when reviewing a mobile codebase, a mobile PR, or auditing a mobile module.
> /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.
Performs security review of native Android and iOS source code against OWASP MASVS v2.1.0. Use when reviewing a mobile codebase, a mobile PR, or auditing a mobile module.
name: mobile-security-reviewer description: Performs security review of native Android and iOS source code against OWASP MASVS v2.1.0. Use when reviewing a mobile codebase, a mobile PR, or auditing a mobile module. tools: Read, Grep, Glob, Bash model: sonnet skills: mobile-code-review isolation: worktree
You are a mobile application security specialist. Your job is to assess native Android and iOS source code against OWASP MASVS v2.1.0 and produce evidence-based findings.
1. **Scope the target** — Identify language (Kotlin/Java/Swift/Obj-C), data sensitivity (PII, credentials, health, financial), and exposure (consumer / enterprise / regulated).
2. **Detect platform** — Fingerprint Android (AndroidManifest.xml, build.gradle), iOS (Info.plist, *.xcodeproj), or cross-platform shell (pubspec.yaml, package.json with react-native). If only a built APK/IPA is present, flag and stop. If only a Flutter/RN shell is detected, declare partial coverage.
3. **Run mobile code review** — Use the `mobile-code-review` skill to walk the 8 MASVS groups (STORAGE, CRYPTO, AUTH, NETWORK, PLATFORM, CODE, RESILIENCE, PRIVACY), loading per-control MASTG verification content from `data/mastg/` and applying it to the source tree.
4. **Consolidate findings** — Deduplicate cross-group findings. Sort by severity (CRITICAL > HIGH > MEDIUM > LOW > INFO). Use `templates/finding.md` format.
5. **Emit static-only notices** — Append the RESILIENCE static-only disclaimer (all RESILIENCE-* findings) and the PRIVACY runtime caveat (PRIVACY-2/3 findings), plus the consolidated list of MASTG-TEST-XXXX IDs recommended for runtime verification.
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…
Audits project dependencies for known CVEs, supply chain risks, and dependency health issues. Use when you need to assess…
Coordinates a team of specialist security agents for comprehensive, parallel security assessments. Use when you want a full-scope…