create-connector

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to populate connector templates which are then passed to the Harness MCP server for resource creation.
  • Ingestion points: User-provided details for connector parameters in SKILL.md instructions.
  • Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore potentially malicious content within user input.
  • Capability inventory: Uses harness_create to create resources and harness_execute to perform actions via MCP.
  • Sanitization: Absent. The skill does not provide mechanisms to sanitize or validate the content of the generated YAML.
  • [SAFE]: The skill uses best practices for secret management by employing secret references (e.g., tokenRef, secretRef, passwordRef) instead of requiring hardcoded credentials in the configuration templates.
  • [SAFE]: No patterns of credential theft, unauthorized network access, or remote code execution were found. All external URLs in templates point to official service endpoints for the intended integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:25 PM
Security Audit — agent-trust-hub — create-connector