frontend-dev

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external bundle hosted on the MiniMax AI official GitHub repository (github.com/MiniMax-AI/skills) for its primary functionality and assets.- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting AI-generated media via the MiniMax API, which represents a surface where untrusted content could influence the agent's behavior.
  • Ingestion points: Data and media content retrieved from the MiniMax API (SKILL.md).
  • Boundary markers: None identified in the skill instructions to delimit external content.
  • Capability inventory: Performs frontend development, generates hero pages, and showcases sites.
  • Sanitization: No explicit sanitization or validation of the API outputs is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:57 PM
Security Audit — agent-trust-hub — frontend-dev