design-slop-check
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for text processing and copy review. Analysis of the instructions and workflow shows no evidence of malicious intent, unauthorized command execution, or data exfiltration.
- [PROMPT_INJECTION]: The skill processes external text and files, creating a surface for indirect prompt injection. However, the agent's actions are limited to providing text-based feedback and suggestions, which mitigates the impact of such attempts. 1. Ingestion points: Raw text input, file paths (PDF, HTML, Text), and Claude Design URLs (SKILL.md, Workflow section). 2. Boundary markers: No specific delimiters or safety warnings for untrusted content are defined in the instructions. 3. Capability inventory: The skill is limited to text analysis and generating suggestions; it does not have access to sensitive tools, file writing, or network operations. 4. Sanitization: No explicit sanitization or filtering of input content is described.
Audit Metadata