space-image2proto
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection because it transforms untrusted external inputs—including UI screenshots and textual requirement descriptions—directly into executable HTML and JavaScript code. Ingestion points include user-provided mockups and feedback processed in the onboarding and core workflow sections of SKILL.md. There are no explicit boundary markers or safety instructions used to delimit user data or instruct the agent to ignore embedded commands. Furthermore, the instructions lack sanitization or validation logic for the input content before it is used to generate or modify prototypes using the Write and Edit tools.
- [EXTERNAL_DOWNLOADS]: For flowchart generation, the skill references the Mermaid.js library from Cloudflare's public CDN (cdnjs.cloudflare.com). This is a well-known and trusted service, and the use of the library follows industry-standard practices.
Audit Metadata