aws-agentcore-langgraph

• Outcome: Pass
• Latest audit: May 28, 2026, 7:38 AM
• Version:
  1.0.2

Overview

This is a coherent AWS AgentCore and LangGraph deployment skill with visible, user-directed cloud commands and memory features.

Install this only if you intend to manage AWS AgentCore/LangGraph deployments. Use a least-privileged AWS profile, confirm the account and region before deploy or destroy commands, prefer dry-run cleanup where available, and define retention, consent, deletion, and tenant-boundary rules before storing conversation memory.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation includes `agentcore destroy` as a cleanup command without any warning that it may irreversibly remove deployed infrastructure and associated resources. In an agent skill context, users may copy-paste CLI commands directly, so omitting a confirmation note increases the risk of accidental teardown, service outage, and data loss.

VirusTotal

66/66 vendors flagged this skill as clean.