establish-visual-hierarchy

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based design guidelines and evaluation criteria. It does not perform any network operations, file system modifications, or command execution.
  • [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety filters were detected. The instructions are focused on UI design principles.
  • [DATA_EXFILTRATION]: There are no patterns involving sensitive file access or data transmission to external domains. The skill operates solely on the provided input data.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts or packages. There are no shell commands or dynamic code evaluation patterns.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied design descriptions, it lacks any functional capabilities (such as network access or command execution) that could be exploited via indirect injection. The attack surface is minimal.
  • Ingestion points: Input fields design_description and element_list defined in the YAML frontmatter.
  • Boundary markers: None provided in the instructions.
  • Capability inventory: None. The skill does not have access to tools, network, or the filesystem.
  • Sanitization: Not applicable as there are no executable actions performed on the input.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:37 AM
Security Audit — agent-trust-hub — establish-visual-hierarchy