The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided parameters to generate YAML configurations for cloud infrastructure, which creates an inherent architectural surface for indirect prompt injection.
Ingestion points: User requests containing trigger names, identifiers, cron expressions, and branch filters (SKILL.md).
Boundary markers: None present; user-provided input is directly interpolated into the YAML template fields without explicit delimiters or 'ignore' instructions.
Capability inventory: The skill uses harness_create, harness_list, and harness_get to interact with and modify the state of the Harness platform (SKILL.md).
Sanitization: The instructions do not describe any sanitization, escaping, or validation of user-provided strings before they are used to build the resource YAML for the harness_create tool.

create-trigger