manage-users

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines clear instructions for administrative management of Harness principals (users, groups, service accounts) using the dedicated harness-mcp-v2 server tools.
  • [SAFE]: All tool calls (harness_list, harness_get, harness_create, harness_delete) are restricted to the Harness platform context.
  • [SAFE]: No evidence of data exfiltration, obfuscation, or unauthorized system access was found.
  • [SAFE]: While the skill ingests user-provided data into tool parameters (e.g., search_term, body), this is a standard administrative interface and does not constitute a vulnerability in the skill's logic itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:16 AM
Security Audit — agent-trust-hub — manage-users