skills/harperfast/skills/harper-mcp/Gen Agent Trust Hub

harper-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a documentation-only resource providing integration guidelines and code examples. It does not contain any executable scripts or autonomous commands that run during the skill's load process.
  • [SAFE]: The skill explicitly emphasizes security best practices, including a 'Hardening Checklist' in security-posture.md that guides users on protecting public endpoints using CORS, rate limiting, and identity validation.
  • [SAFE]: The code snippets provided (JavaScript/TypeScript for MCP tools and resources) include defensive programming patterns, such as verifying user context (context.user) and warning against path traversal when constructing filesystem paths from URI templates.
  • [SAFE]: Examples of configuration (harper-config.yaml) and network requests (curl) use standard documentation placeholders (e.g., admin:password, localhost) for educational purposes and do not represent a credential exposure risk for actual deployments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 03:58 PM
Security Audit — agent-trust-hub — harper-mcp