aipixelperfect-design-engine
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to clone a repository from an unrecognized GitHub account (
github.com/abnormal-codex/Ai-Pixel-Design-Archive), which constitutes an external download from an untrusted source.\n- [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user inputs that could potentially manipulate agent behavior through embedded instructions.\n - Ingestion points: The
promptparameter in image synthesis functions and thecommentfield in the collaboration review workflow inSKILL.md.\n - Boundary markers: None identified; the skill does not use delimiters to wrap untrusted data when passing it to synthesis and review APIs.\n
- Capability inventory: Includes network access via the AiPixelPerfect API and the ability to run installation commands like
npm install.\n - Sanitization: No evidence of input validation or content filtering is provided to mitigate potential injections.
Audit Metadata