a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Review a mobile app (Android/iOS) against the OWASP MASVS control groups — storage, crypto, auth, network, platform, code quality, and resilience — producing a per-control finding set. Use for a structured mobile security assessment or design review. Authorized testing only.
$ npx -y skills add jassics/awesome-claude-security --skill masvs-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/masvs-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review a mobile app (Android/iOS) against the OWASP MASVS control groups — storage, crypto, auth, network, platform, code quality, and resilience — producing a per-control finding set. Use for a structured mobile security assessment or design review. Authorized testing only.
name: masvs-review description: >- Review a mobile app (Android/iOS) against the OWASP MASVS control groups — storage, crypto, auth, network, platform, code quality, and resilience — producing a per-control finding set. Use for a structured mobile security assessment or design review. Authorized testing only.
A MASVS-aligned assessment: each control group examined, with applicability, evidence, severity, and remediation.
not a substitute for the above).
1. Gather artifacts: the app package (APK/IPA), and source if available. 2. Walk each control group; for static checks, cross-ref `sast-sca`; for runtime, use `mobile-pentest`. 3. Record per control: applicable? · finding · evidence · severity · remediation. 4. Score (`security-reporting:cvss`) and rank.
A per-control table grouped by MASVS category + ranked top risks. Confirmed issues → `security-reporting:finding`.
The highest-frequency mobile issues are insecure data storage and weak network/TLS handling (broken cert validation, no pinning where warranted). Treat RESILIENCE as defense-in-depth — never as a replacement for fixing storage/crypto/auth. Test only apps you're authorized to assess.
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.
Repo: jassics/awesome-claude-security
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Test the agent execution harness/runtime itself — LangChain/LangGraph, AutoGen, CrewAI, custom ReAct-style loops, or computer-use/browser-use agents — for…
Assess an autonomous / tool-using AI agent for security end-to-end: tool privileges, autonomy and approval boundaries, excessive agency, memory/state…
Test what an AI agent will actually do without human confirmation, including under injected-goal / prompt-injection scenarios, to validate its autonomy and…
Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description and result poisoning,…
Inventory the tools/functions an AI agent can call and audit their privileges, side effects, and approval requirements to find excessive-agency and…