typography-director
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and protect exact user copy strings during layout operations. While it lacks explicit delimiters (like triple backticks or XML tags) to separate user data from instructions, its primary output is a structured design signal packet rather than executable code or sensitive file operations, limiting the impact of potential injection. Ingestion occurs via user copy strings in SKILL.md, and no sanitization mechanisms are explicitly defined within the provided text.
Audit Metadata