manage-delegates

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate management tool for the Harness platform and does not contain malicious code, hardcoded credentials, or unauthorized network activity.\n- [PROMPT_INJECTION]: The skill has a standard interaction surface where it processes user-provided inputs for resource management tasks, which is an inherent property of management skills.\n
  • Ingestion points: User-supplied values for organization, project, and token identifiers in SKILL.md.\n
  • Boundary markers: None explicitly defined in the instruction set.\n
  • Capability inventory: The skill enables listing, creating, and deleting delegate tokens via the harness-mcp-v2 server.\n
  • Sanitization: Relies on the input validation mechanisms of the underlying MCP tools and Harness API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 06:18 AM
Security Audit — agent-trust-hub — manage-delegates