skills/davidlee/doctrine/design/Gen Agent Trust Hub

design

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a legitimate workflow for software design and architectural analysis. Its primary function is to transform intent into implementable design documents using an iterative process.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external artifacts (slice folders, research, and design docs), which is an inherent part of its design-focused mission.
  • Ingestion points: Existing slice folders, design artifacts, and research material.
  • Boundary markers: The skill does not define specific delimiters for untrusted content.
  • Capability inventory: Capabilities include writing to the filesystem (design.md) and executing platform CLI commands (doctrine).
  • Sanitization: The skill does not describe specific sanitization steps for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 10:00 AM
Security Audit — agent-trust-hub — design