langgraph-agentcore
Production patterns for LangGraph StateGraph workflows deployed on AWS Bedrock AgentCore. Use when building agentic AI workflows with LangGraph, deploying agents to AgentCore Runtime, adding interrupt-based human-in-the-loop review, or checkpointing workflows that run for days. Covers graph design, interrupt() HITL, checkpointing, 3-tier model routing with fallback chains, confidence calibration, Cedar policy enforcement, cost-aware pipeline design, Bedrock Foundation Models and Guardrails, MCP tools via AgentCore Gateway, and observability with LangSmith and CloudWatch. Not for insurance underwriting domain rules — see underwriting.
74
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow reads external memory records and past interactions via MemoryClient, which can contain outsider-authored content across sessions.
- Repository
provectus/awos-recruitment
- Revision
ce6a3ea
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.