blutui-project-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests untrusted project data and performs actions based on that content, creating a potential injection surface.
  • Ingestion points: The agent is instructed to read and process files including tailwind.config.*, postcss.config.*, and any files found within a pages/ directory to facilitate style system detection and page migration (AGENTS.md, rules/foundation-file-structure.md).
  • Boundary markers: There are no instructions for the agent to use delimiters or to disregard potential instructions embedded within the files being processed.
  • Capability inventory: The agent is granted access to Blutui MCP tools (e.g., create_page, list_pages) and file system operations, including the mandatory deletion of files during migration (rules/mcp.md, rules/foundation-file-structure.md).
  • Sanitization: The skill lacks requirements for sanitizing or validating the content extracted from external project files before it is used to drive agent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:33 PM
Security Audit — agent-trust-hub — blutui-project-guidelines