moai-domain-frontend

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by fetching external documentation that could influence the agent's behavior.
  • Ingestion points: The FrontendArchitectOptimizer class utilizes the mcp__context7__get-library-docs tool in SKILL.md to retrieve external documentation strings.
  • Boundary markers: The skill lacks explicit delimiters or safety instructions when processing the external documentation, which may allow embedded instructions to override system prompts.
  • Capability inventory: The agent is equipped with powerful tools such as Bash, Write, and Edit, which could be misused if an injection occurs.
  • Sanitization: No sanitization or validation logic is applied to the content retrieved from the external documentation source.
  • [EXTERNAL_DOWNLOADS]: The skill performs network-based operations to retrieve documentation and assets.
  • MCP Documentation: It retrieves technical documentation for frameworks like React and Next.js via the mcp__context7__get-library-docs tool.
  • User Assets: UI components in SKILL.md reference the well-known service api.dicebear.com to fetch SVG avatar resources based on user IDs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM