launchdarkly-factory-settings
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by LaunchDarkly and is designed to interact specifically with LaunchDarkly's infrastructure and the @launchdarkly/mcp-server tool. All external resources, including documentation links and software dependencies, are owned and managed by the vendor.
- [SAFE]: Instructions include mandatory human-in-the-loop verification (the 'Confirm before write' workflow) which ensures that the agent cannot modify production settings without explicit, turn-by-turn user approval.
- [SAFE]: The skill enforces a 'least privilege' approach, instructing the agent not to enable sensitive capabilities like auto-releasing or changing approval gates unless specifically requested by the user.
Audit Metadata