screenshot-to-code
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided screenshots, which constitutes an ingestion point for untrusted data. If a screenshot contains malicious instructions, the agent could potentially be influenced. However, because the skill's capabilities are restricted to code generation without access to the file system or network, the potential impact is negligible.
- Ingestion points: User-provided screenshots (SKILL.md).
- Boundary markers: None present.
- Capability inventory: No dangerous capabilities; the skill only generates text/code output.
- Sanitization: No visual or OCR sanitization is specified for processing the image content.
Audit Metadata