simple-human-writing-style

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the betterprompt package from the official repository of the vendor, BetterPromptme, which is used to execute the writing tasks.
  • [COMMAND_EXECUTION]: The skill invokes the betterprompt command-line interface to discover model capabilities and to generate simplified text from user inputs.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external text inputs into the writing workflow.
  • Ingestion points: Content, purpose, and extra_notes input variables defined in SKILL.md.
  • Boundary markers: No specific delimiters are identified to isolate the processed content.
  • Capability inventory: Executes the betterprompt generate shell command.
  • Sanitization: User inputs are interpolated into the command parameters without explicit validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 12:07 AM