a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity,…
Run a MASTG-based mobile penetration test (Android/iOS) combining static and dynamic analysis: storage inspection, traffic interception, platform-interaction abuse, and resilience checks. Use to actively test a mobile app you're authorized to assess.
Claude Code
$ npx -y skills add jassics/awesome-claude-security --skill mobile-pentest --agent claude-code
Codex
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a codex -y
Cursor
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a cursor -y
Gemini CLI
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a gemini-cli -y
GitHub Copilot
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a github-copilot -y
OpenCode
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a opencode -y
Windsurf
$ npx skills add jassics/awesome-claude-security --skill mobile-pentest -a windsurf -y
name: mobile-pentest description: >- Run a MASTG-based mobile penetration test (Android/iOS) combining static and dynamic analysis: storage inspection, traffic interception, platform-interaction abuse, and resilience checks. Use to actively test a mobile app you're authorized to assess.
Evidence-backed mobile findings from hands-on static + dynamic testing, mapped to MASVS controls and ranked.
traffic interception. Keep testing within scope and non-destructive.
1. **Recon & static** — unpack the app; review manifest/Info.plist, permissions, exported components, secrets/keys in code or resources, and dependencies (cross-ref `sast-sca`). 2. **Storage** — inspect on-device data: shared prefs/UserDefaults, databases, files, keychain/keystore, caches, logs, backups, clipboard. 3. **Network** — intercept traffic; test TLS, certificate validation, and pinning (including pinning-bypass to assess robustness); look for cleartext/sensitive data. 4. **Platform interaction** — exercise exported activities/services, deep links, intent/IPC handling, WebView config (JS bridges, file access). 5. **Auth & session** — local auth/biometric bypass, token storage, session handling against the backend (`api-security`). 6. **Resilience** (if in scope) — root/jailbreak detection, anti-tamper, debugging.
Work the methodology; record per finding: control · technique · evidence · impact · remediation. Keep payloads benign and within scope.
A findings table mapped to MASVS groups, ranked by severity. Confirmed issues → `security-reporting:finding`.
Mobile risk usually concentrates at the client↔backend boundary — pair this with `api-security` for the server side. Pinning-bypass and root-detection-bypass are to assess control robustness, not to attack out-of-scope systems.
A Claude Code plugin marketplace for the full cybersecurity & GenAI-security lifecycle — from recon and threat modeling to detection engineering, GRC, and CISO-level strategy. A pentester knows which OWASP test bends a broken-access-control endpoint.
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity,…
Test the agent execution harness/runtime itself — LangChain/LangGraph, AutoGen, CrewAI, custom ReAct-style loops, or…
Assess an autonomous / tool-using AI agent for security end-to-end: tool privileges, autonomy and approval boundaries, excessive…
Test what an AI agent will actually do without human confirmation, including under injected-goal / prompt-injection scenarios, to…
Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description…
Inventory the tools/functions an AI agent can call and audit their privileges, side effects, and approval requirements to find…
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…