markdown-design

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided Markdown files when in 'Retrofit mode', creating a surface for indirect prompt injection.\n
  • Ingestion points: The skill is instructed to read and inventory existing files for upgrade opportunities via the /markdown-design path-to-file command defined in SKILL.md.\n
  • Boundary markers: The instructions do not provide specific delimiters or 'ignore embedded instructions' warnings to isolate external file content from the agent's logic.\n
  • Capability inventory: The skill's capabilities are restricted to document analysis and local file rewriting; it does not have shell execution or network operation capabilities.\n
  • Sanitization: There are no instructions for sanitizing or validating the contents of the files being redesigned.\n- [SAFE]: The skill references img.shields.io in references/visual-elements.md and references/templates.md for generating project status badges. This is a well-known and standard service for project documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 08:42 PM
Security Audit — agent-trust-hub — markdown-design