skill-authoring

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown content. It does not include any scripts, executables, or configuration files that would allow for command execution or remote code execution.
  • [EXTERNAL_DOWNLOADS]: The documentation refers to a GitHub repository within the author's own organization (rebuildup/design-skills) for context and methodology. This is a legitimate reference to a well-known service and the vendor's own resource.
  • [INDIRECT_PROMPT_INJECTION]: Although the skill outlines a process for ingesting external research and user requests, it mandates strict verification protocols—including 'real-artifact trials' and 'cold-reader verification'—which serve as essential filters to prevent the propagation of malicious or incorrect instructions into generated skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 11:17 PM