skills/muris11/prd-kit/prd-design/Gen Agent Trust Hub

prd-design

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a template-driven design assistant that guides the agent through a user questioning flow to establish visual direction for software projects. It uses standard file system tools to update documentation and does not contain any code execution, network requests, or obfuscation.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect injection surface as it processes user-provided application ideas to recommend design styles and generate content for local files.
  • Ingestion points: User-supplied 'app idea' and template selections described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands in user input are defined.
  • Capability inventory: Frontmatter allows the use of Read, Write, Edit, Glob, and Grep tools to modify local project files (DESIGN.md and PRD documents).
  • Sanitization: The instructions do not specify any validation or sanitization procedures for the input provided by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:24 AM
Security Audit — agent-trust-hub — prd-design