better

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a reference markdown file from raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/create-software/references/design-system-rules.md. This is a vendor-owned resource used for design principles and does not involve executable code.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection due to its interaction with untrusted local project data.
  • Ingestion points: The agent reads project documentation files such as CONTRIBUTING.md and AGENTS.md, as well as application source code and Storybook files.
  • Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" prompts to separate data from system instructions.
  • Capability inventory: The skill has the ability to read project files and perform file write operations to implement UI fixes.
  • Sanitization: No sanitization, escaping, or validation of the ingested project content is performed before processing it for implementation work.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 04:34 PM