a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity,…
Assess the network protocols and services in use for security weaknesses — cleartext protocols, weak/outdated crypto and TLS, insecure or legacy services, and man-in-the-middle exposure. Use to review what's running on the network and how securely it communicates.
Claude Code
$ npx -y skills add jassics/awesome-claude-security --skill protocol-security-review --agent claude-code
Codex
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a codex -y
Cursor
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a cursor -y
Gemini CLI
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a gemini-cli -y
GitHub Copilot
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a github-copilot -y
OpenCode
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a opencode -y
Windsurf
$ npx skills add jassics/awesome-claude-security --skill protocol-security-review -a windsurf -y
name: protocol-security-review description: >- Assess the network protocols and services in use for security weaknesses — cleartext protocols, weak/outdated crypto and TLS, insecure or legacy services, and man-in-the-middle exposure. Use to review what's running on the network and how securely it communicates.
A view of where network communications and services are weak — unencrypted, weakly encrypted, or inherently insecure — with concrete upgrades.
1. **Cleartext protocols** — Telnet, FTP, HTTP, SNMPv1/2c, unencrypted LDAP/POP3/ IMAP/SMTP, rsh — anything carrying credentials or data in the clear. 2. **TLS/crypto quality** — protocol versions (no SSLv3/TLS1.0/1.1), weak ciphers, expired/self-signed/mismatched certs, weak key exchange, missing forward secrecy. 3. **Insecure/legacy services** — SMBv1, weak NTLM, LLMNR/NBT-NS, deprecated services that should be disabled; default credentials/community strings. 4. **MITM exposure** — name-resolution poisoning (LLMNR/NBT-NS/mDNS), missing SMB signing, lack of network auth (802.1X), rogue-device risk. 5. **Service exposure** — sensitive services reachable from untrusted zones (cross-ref `network-segmentation-review`).
1. Inventory services/protocols in scope (from `network-pentest` enumeration or config review). 2. Assess each against the checks above; capture protocol, weakness, and exposure. 3. Recommend the secure replacement (e.g. SSH for Telnet, SNMPv3, TLS1.2+/1.3, disable SMBv1, enable signing, deploy 802.1X) and where to enforce it.
A table: service/protocol · weakness · exposure · severity · secure replacement. Confirmed issues → `security-reporting:finding`.
Cleartext credentials on the wire and name-resolution poisoning (LLMNR/NBT-NS) are classic, high-impact, and common — prioritize them. Disabling legacy protocols (SMBv1, SSLv3/TLS1.0) is usually a high-value, low-friction win.
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…