Stats
Actions
Tags
From prodsec-skills
Enforces SPIFFE/SPIRE plus mTLS for authenticating agent-to-agent communication. Use when designing or reviewing multi-agent system security.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prodsec-skills:agent-to-agent-authThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Agent-to-agent communication MUST follow the service-to-service recommendation and implement SPIFFE/SPIRE+mTLS.
Agent-to-agent communication MUST follow the service-to-service recommendation and implement SPIFFE/SPIRE+mTLS.
Agent A Agent B
│ │
├── SPIFFE ID: ├── SPIFFE ID:
│ spiffe://domain/agent/a │ spiffe://domain/agent/b
│ │
├── Gets SVID from SPIRE Agent ├── Gets SVID from SPIRE Agent
│ │
└── mTLS connection ────────────→└── Validates Agent A's SVID
(presents SVID) (presents own SVID)
Use a consistent SPIFFE ID naming convention:
spiffe://<trust-domain>/agent/<agent-type>/<instance-id>
Examples:
spiffe://example.com/agent/data-analyst/prod-01spiffe://example.com/agent/code-reviewer/staging-02npx claudepluginhub redhatproductsecurity/prodsec-skills --plugin prodsec-skillsEnforces SPIFFE/SPIRE plus mTLS for service-to-service authentication. Use when designing, building, or reviewing authentication between services, workloads, or machines in AI systems.
Detects agent-to-agent calls missing authentication, authorization, or permission scoping. Use when building multi-agent pipelines, spawning subagents, or delegating tasks between LLM agents.
Implements A2A authentication schemes—API keys, Bearer tokens, OAuth 2.0, OpenID Connect, mutual TLS—for securing agent-to-agent communication and Agent Card security declarations.