best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of untrusted user data without sufficient defensive measures.
- Ingestion points: Instructions in SKILL.md direct the agent to pass the "user's words and attachments" directly to subsequent processing steps.
- Boundary markers: The skill lacks requirements for using delimiters (e.g., XML tags or backticks) or explicit instructions for the agent to ignore any embedded directives in user data.
- Capability inventory: The skill enables the use of tools for searching design patterns, comparing applications, and generating redesign variations.
- Sanitization: There are no instructions to sanitize or validate the content of user-provided text or files.
- [NO_CODE]: The skill consists entirely of Markdown files for documentation and instruction. No scripts, binaries, or active configuration files are present.
Audit Metadata