launchdarkly-flag-cleanup
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust 'Safety First' workflow that requires explicit human confirmation before the agent performs any code modifications or pull request creations, mitigating risks of unintended changes.
- [SAFE]: It utilizes a remote Model Context Protocol (MCP) server for all LaunchDarkly interactions. This ensures that the agent uses the official LaunchDarkly API as the source of truth for flag status, rather than making assumptions based on local code or environment variables.
- [SAFE]: All external resources, including dependencies like @launchdarkly/mcp-server and documentation links to docs.launchdarkly.com, originate from the official vendor infrastructure, following security best practices for resource sourcing.
Audit Metadata