agent-graphs

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions for managing multi-agent graph topologies using LaunchDarkly's MCP tools. All operations, such as creating, updating, and browsing graphs, are performed through dedicated tools like create-agent-graph and get-agent-graph.
  • [SAFE]: No malicious patterns, such as prompt injection, obfuscation, or unauthorized data access, were detected. The instructions follow standard practices for managing graph structures.
  • [SAFE]: The external resource referenced (LaunchDarkly MCP server) is an official requirement consistent with the skill's stated purpose and the identified author.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 10:00 PM
Security Audit — agent-trust-hub — agent-graphs