The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for managing configuration-as-code within the es-triggers ecosystem. All script examples provided are functional snippets for the platform and use placeholder domains for external service calls.
[DATA_EXPOSURE]: The skill and its associated documentation do not contain hardcoded credentials, secrets, or paths to sensitive local system files. Example configurations use non-existent domains like 'example.com' for API endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill defines a system that processes untrusted external data (HTTP webhooks). While this represents a potential attack surface, it is the primary and intended purpose of the es-triggers platform.
Ingestion points: headers, body, and query variables in binding.md and source-interceptor.md.
Boundary markers: The skill does not explicitly provide instructions for boundary marking, but the system's design separates variables from templates.
Capability inventory: The platform supports network operations via the api() function and state management via redis.
Sanitization: Instructions focus on logic and transformation; sanitization of external input is left to the user's implementation.
[REMOTE_CODE_EXECUTION]: While the skill facilitates the creation of executable JavaScript for the es-triggers platform, it does not use dangerous patterns such as 'curl | bash' or 'eval' of untrusted remote content. All script generation is based on the platform's specific API surface.

trigger-config-writer