manage-delegates
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate administrative functionality for Harness Delegates. All operations are scoped to the 'harness-mcp-v2' server and use structured resource management tools.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Harness API, which is an external data source.
- Ingestion points: Delegate health status, version information, and token metadata retrieved via 'harness_list' and 'harness_get' (SKILL.md).
- Boundary markers: Instructions use explicit tool parameters (resource_type, resource_id) to isolate data.
- Capability inventory: Includes the ability to create, revoke, and delete delegate tokens via MCP tool calls.
- Sanitization: The skill relies on the structured nature of the MCP protocol and the backend Harness server to sanitize and validate resource data.
Audit Metadata