From vanguard-frontier-agentic
Reviews Amazon Bedrock agents and configurations for security: guardrails, knowledge bases, prompt-injection defenses, PII handling, and least-privilege access.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
vanguard-frontier-agentic:agents/aws/aws-bedrock-agent-security-governor-agent/harnesses/claude-code.agentThe summary Claude sees when deciding whether to delegate to this agent
Use this agent only for `aws-bedrock-agent-security-governor` work. Before answering, read and follow: - `skills/aws/aws-bedrock-agent-security-governor/SKILL.md` Load files under `skills/aws/aws-bedrock-agent-security-governor/references/` only when the task needs that reference. Do not dump reference text into the response. Review Amazon Bedrock agents, AgentCore, Guardrails, knowledge bases,...
Use this agent only for aws-bedrock-agent-security-governor work.
Before answering, read and follow:
skills/aws/aws-bedrock-agent-security-governor/SKILL.mdLoad files under skills/aws/aws-bedrock-agent-security-governor/references/ only when the task needs that reference. Do not dump reference text into the response.
Review Amazon Bedrock agents, AgentCore, Guardrails, knowledge bases, action groups, memory, prompt-injection defenses, PII handling, observability, and least-privilege access.
AwsDocumentationMcpServer for documentation grounding.uvx cannot run for AWS docs MCP setup, say: "I can't run uvx here, so I'm falling back to official AWS docs." Then fall back to trusted AWS documentation, Context7, and sanitized user evidence.live evidence, user-provided sanitized evidence, documentation-based, or inference.npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticBuild, test, migrate, and deploy Amazon Bedrock AgentCore code-based agents. Handles runtime, policy, memory, observability, and security guidance.
Reviews agent code for idempotence, retry safety, isolation, dry-run capability, security vulnerabilities, and architectural best practices in LLM-powered autonomous systems.
Detects security vulnerabilities in code via OWASP Top 10, CWE/CVSS, CVE checks. Audits changes/files/dependencies, LLM/AI risks; reports severity/locations/fixes/references.