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_create and harness_list tools 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
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:24 PM
Security Audit — agent-trust-hub — create-trigger