polish
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of purely instructional markdown files and research references. It does not include any executable scripts, binaries, or automated shell commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify external project code and UI components, which creates a surface for indirect prompt injection.\n
- Ingestion points: The agent is directed to read repository routes, component trees, global styles, and tokens as outlined in SKILL.md and references/audit.md.\n
- Boundary markers: No explicit data delimiters are defined for untrusted external content, though the skill sets strong operational boundaries to preserve existing design systems and APIs.\n
- Capability inventory: The skill describes the intent to perform file modifications (token and style updates), but no implementation logic or subprocess calls are present in the skill files.\n
- Sanitization: There are no specific instructions for sanitizing or escaping content ingested from external source code.
Audit Metadata