mongodb-schema-design

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill integrates with a MongoDB MCP server to retrieve and process data from database collections, which introduces a surface for indirect prompt injection. Malicious instructions stored in the database could potentially influence agent behavior.
  • Ingestion points: Data enters the context via MCP tools including mcp__mongodb__collection-schema, mcp__mongodb__aggregate, and find as described in SKILL.md.
  • Boundary markers: The skill includes an 'Action Policy' section in SKILL.md that explicitly requires user confirmation before performing write or destructive operations.
  • Capability inventory: The skill can perform database reads, schema analysis, and user-approved updates or deletions (documented in SKILL.md and reference files).
  • Sanitization: There is no mention of explicit sanitization or filtering of database content before it is used in agent prompts.
  • [EXTERNAL_DOWNLOADS]: The skill references the official MongoDB MCP Server repository (github.com/mongodb-js/mongodb-mcp-server) for database verification. This is an integration with a resource provided by the skill's author and a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 03:07 PM
Security Audit — agent-trust-hub — mongodb-schema-design