security-report

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for the agent to use Harness-specific MCP tools (harness_list, harness_get, harness_create, harness_execute) to manage security issues, SBOMs, and compliance results. These actions are consistent with the developer's stated purpose.
  • [SAFE]: There are no detected instances of prompt injection, data exfiltration, or obfuscation. The skill correctly utilizes placeholders for sensitive identifiers like organization and project IDs.
  • [SAFE]: No external code execution or unauthorized dependency installations were found. All operations are confined to the defined MCP toolset provided by the Harness vendor.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:16 AM
Security Audit — agent-trust-hub — security-report