create-service

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the user's codebase (file names and Dockerfile contents) to automate service configuration.
  • Ingestion points: Scans project directories and files (e.g., k8s/, Dockerfile) as described in SKILL.md.
  • Boundary markers: The skill includes a 'Confirm with user' step before executing tool calls.
  • Capability inventory: Performs service creation and listing via the Harness MCP server tools harness_create and harness_list.
  • Sanitization: Relies on human-in-the-loop confirmation of the generated YAML before resource creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:24 PM
Security Audit — agent-trust-hub — create-service