ae-ltd-visual-regression-forge
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of instructions and configuration metadata. No shell commands, automated scripts, or external dependencies are included in the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and analyzing external UI content, which represents a standard but low-risk attack surface:
- Ingestion points: Targeted web pages and UI components defined in the snapshot scope (SKILL.md).
- Boundary markers: Not explicitly defined in the provided prompt instructions.
- Capability inventory: Limited to UI analysis, pixel-diff reporting, and mapping failures to CSS/layout fixes (SKILL.md). No file-write, network, or command execution capabilities are granted by the skill itself.
- Sanitization: No explicit sanitization or filtering of captured UI content is described.
Audit Metadata