skills/ynz012x/skills/system-design/Gen Agent Trust Hub

system-design

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable scripts, binaries, or external network requests. All functionality is defined through high-quality instructional prompts and documentation templates.
  • [PROMPT_INJECTION]: The skill uses 'Step 3.1: Existing Codebase Analysis' to scan local source code. This introduces an indirect prompt injection surface where the AI might encounter malicious instructions embedded in file comments. However, the skill lacks write permissions or network tools to act on such injections, and the analysis is restricted to generating design documentation.
  • Ingestion points: Local file system content accessed via the user-provided project_path parameter (SKILL.md).
  • Boundary markers: The instructions do not provide explicit delimiters to differentiate code content from agent instructions during analysis.
  • Capability inventory: Limited to directory scanning and text analysis for documentation generation. No capabilities for shell execution, network egress, or persistent file modification are requested or used.
  • Sanitization: No specific content filtering or sanitization logic is implemented for the ingested codebase data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:26 AM