The Agent Skills Directory

[PROMPT_INJECTION]: The skill manages external prompt content from the LaunchDarkly platform, creating a surface for indirect prompt injection.
Ingestion points: Data enters the agent context through tools like list-prompt-snippets and get-prompt-snippet used in SKILL.md.
Boundary markers: The instructions do not explicitly define delimiters for external content.
Capability inventory: The skill can modify snippets and configurations using update-prompt-snippet and update-ai-config-variation.
Sanitization: No explicit sanitization or validation of the remote prompt text is described in the workflow.

aiconfig-snippets