ui-typography

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill mandates a silent enforcement mode that instructs the agent to apply typographic rules without asking for permission or providing explanations, which overrides standard agent interaction protocols.
  • [COMMAND_EXECUTION]: The documentation provides shell command templates, specifically using sed, for automated text replacement in source files.
  • [PROMPT_INJECTION]: The skill includes an audit mode for processing untrusted external code. Ingestion points: User-provided legacy code and interface artifacts. Boundary markers: Absent. Capability inventory: Includes shell command templates for file modification (sed). Sanitization: No input validation or escaping mechanisms are defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 11:36 PM