quick-design

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied descriptions and reads existing project documentation to generate new design files.
  • Ingestion points: The argument-hint provided by the user and files located in design/gdd/, design/quick-specs/, and assets/data/ (referenced in SKILL.md).
  • Boundary markers: None identified. The skill interpolates content directly into markdown templates without specific delimiters to isolate external text from instructions.
  • Capability inventory: The skill utilizes Read, Glob, Grep, Write, and Edit tools to interact with the local filesystem.
  • Sanitization: No explicit sanitization or validation of the ingested text is performed before interpolation.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized external communications were detected. The skill's operations are limited to local file management within a defined project scope, which is consistent with its primary purpose of design specification authoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:31 PM