launchdarkly-metric-choose
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly advisory. It explicitly mentions that it does not create metrics, attach them to experiments, or configure rollouts, which limits its operational scope and potential for misuse.
- [SAFE]: The skill utilizes official LaunchDarkly MCP tools (
list-metrics,list-metric-events,list-release-policies) to fetch necessary project context. These tools are used solely for information retrieval to support the recommendation workflow. - [SAFE]: There are no detected patterns of prompt injection, data exfiltration, or obfuscation. The logic focuses on analyzing existing metric health (event flow) and providing structured guidance based on industry best practices.
- [SAFE]: The skill references other vendor-owned skills for modification tasks, maintaining a modular and clear separation of concerns.
Audit Metadata