create-trigger
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured templates for Harness CI/CD triggers. All external tools and endpoints refer to the author's own infrastructure (harness-mcp-v2).
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied values to generate YAML configurations for the Harness platform. This represents a low-severity risk surface inherent to the skill's purpose.
- Ingestion points: User-provided trigger names, branch filters, and cron expressions processed within SKILL.md.
- Boundary markers: Absent; the YAML templates do not use specific delimiters to separate user input from the rest of the configuration.
- Capability inventory: Uses harness_create and harness_list tools via the Harness MCP server to manage platform resources (SKILL.md).
- Sanitization: Not explicitly defined in the skill logic.
Audit Metadata