agentcore-investigation

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures MCP servers using uvx to fetch awslabs.cloudwatch-mcp-server and awslabs.cloudwatch-applicationsignals-mcp-server. These are official packages from the skill's author.- [COMMAND_EXECUTION]: Setup documentation includes standard shell commands for environment configuration and repository cloning from the author's GitHub. The agent definition includes execute_bash for operational capabilities.- [SAFE]: No unauthorized data exfiltration, obfuscation, or malicious instructions were detected. The skill's logic is consistent with its stated purpose of log analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 05:15 AM