debug-visual
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external files which influence its automated code modifications. \n
- Ingestion points: Reads user-specified screenshot files, Figma export files, and component source code (SKILL.md). \n
- Boundary markers: Missing explicit instructions or delimiters to isolate data from potential instructions within ingested files. \n
- Capability inventory: Includes the ability to modify source code and trigger hot-reloads of the application (SKILL.md). \n
- Sanitization: No validation or sanitization of content read from external sources is specified.
Audit Metadata