skills/dyrits/skills/codebase-design/Gen Agent Trust Hub

codebase-design

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The 'Design It Twice' workflow described in DESIGN-IT-TWICE.md involves creating technical briefs from user requirements to drive sub-agents.
  • Ingestion points: Technical briefs derived from user input for sub-agents (DESIGN-IT-TWICE.md).
  • Boundary markers: No specific delimiters or safety warnings for the sub-agent briefs are defined.
  • Capability inventory: The skill itself contains no executable code or tool definitions; it provides purely instructional content.
  • Sanitization: No explicit sanitization or filtering of user-provided briefs is described.
  • [NO_CODE]: The skill package is composed entirely of documentation and metadata files. There are no executable scripts, binaries, or automated tool configurations that could perform unauthorized system actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 01:53 PM