create-agent

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a default container image located at pkg.harness.io/vrvdt5ius7uwygso8s0bia/harness-agents/harness-ai-agent:latest. This is a vendor-owned repository managed by Harness, used to power the agents being created.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use harness_create, harness_update, harness_list, and harness_get tools. These are standard management operations within the harness-mcp-v2 environment for its intended use case.
  • [SAFE]: Includes a robust security control requiring an interactive review process. The agent is explicitly instructed to show the generated YAML configuration to the user and wait for confirmation before performing any write operations via MCP tools.
  • [SAFE]: Configuration templates utilize placeholders (e.g., your_llm_connector_id) for sensitive connector references, ensuring that users must explicitly provide their own secure resource identifiers rather than using hardcoded secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:16 AM
Security Audit — agent-trust-hub — create-agent