agent-graphs

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill guides the user through designing and implementing multi-agent workflows using LaunchDarkly's agent graph feature. It utilizes official tools like create-agent-graph, get-agent-graph, and update-agent-graph which are managed via the LaunchDarkly MCP server.
  • [SAFE]: All identified tools and workflows trace back to the author's (launchdarkly) own infrastructure and represent normal vendor functionality for configuration and orchestration.
  • [SAFE]: No malicious patterns such as obfuscation, credential exfiltration, or unauthorized command execution were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:05 PM
Security Audit — agent-trust-hub — agent-graphs