create-pipeline

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes specialized MCP tools (harness_create, harness_update, harness_get, harness_list) provided by the harness-mcp-v2 server to manage pipeline resources on the Harness platform.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it parses untrusted data from local project files (e.g., package.json, go.mod, pom.xml, and existing CI/CD configurations) to automate pipeline generation.
  • Ingestion points: Metadata files and configuration scripts found within the user's codebase (documented in references/codebase-analysis.md).
  • Boundary markers: The instructions do not define specific delimiters for parsed data but emphasize a "Clarify requirements" step to confirm auto-detected settings with the user.
  • Capability inventory: Access to harness_create and harness_update which can modify remote pipeline configurations.
  • Sanitization: The skill relies on the agent's interaction with the user to validate detected settings before committing them to the Harness platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:16 AM
Security Audit — agent-trust-hub — create-pipeline