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