The Agent Skills Directory

[SAFE]: The skill functions as a router for product analytics tasks (A/B testing, funnel analysis, etc.). No security violations such as hardcoded credentials, malicious command execution, or unauthorized network activity were found.
[PROMPT_INJECTION]: The skill ingests untrusted user input via the {{args}} parameter to determine which sub-skill to invoke. While this represents a surface for indirect prompt injection, it is a standard implementation for a dispatcher and does not include instructions that bypass safety filters or override agent behavior.

lumen