design-principles

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard utilities like git, ls, and grep to perform structural analysis and search for patterns within the local codebase.
  • [EXTERNAL_DOWNLOADS]: The skill references npx markdownlint-cli to ensure the generated audit report follows markdown best practices. This involves downloading the linter from the NPM registry, which is a well-known and trusted service.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted codebase files during the audit process.
  • Ingestion points: Source code files across the entire repository being audited.
  • Boundary markers: The skill instructions demand specific file:line evidence for each finding, focusing the agent on objective code patterns.
  • Capability inventory: The skill is limited to reading the local filesystem and writing the final DESIGN_AUDIT.md report.
  • Sanitization: The agent runs markdownlint on the generated report to validate the structure of the output before presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 09:59 AM