interaction-to-next-paint
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely educational and instructional in nature. It provides guidance on improving web responsiveness using standard techniques like Web Workers, task chunking, and layout thrashing avoidance.
- [INDIRECT_PROMPT_INJECTION]: The skill has a theoretical attack surface because it instructs the agent to process and review external project files (routes, assets, and loading behavior). However, this is inherent to its purpose as a performance auditor.
- Ingestion points: External source code and assets are ingested during the Code Review phase described in
SKILL.md. - Boundary markers: None specified in the instructions.
- Capability inventory: The skill does not possess any dangerous capabilities such as file writing, network exfiltration, or arbitrary command execution.
- Sanitization: No specific sanitization of the input code is defined, but the lack of exploitable tools makes this a negligible risk.
Audit Metadata