create-trigger
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes natural language user input to generate structured YAML configurations for external systems.
- Ingestion points: User requests describing trigger types (Webhook, Scheduled, Artifact), branch filters, and payload conditions (SKILL.md).
- Boundary markers: No specific delimiters or "ignore instructions" markers are provided for the generated YAML content.
- Capability inventory: The skill utilizes
harness_createandharness_listtools to interact with the Harness platform (SKILL.md). - Sanitization: No explicit sanitization or validation logic is defined within the skill instructions for the user-provided parameters used in YAML generation.
Audit Metadata