web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and the provided guidelines contain no malicious patterns, obfuscation, or unauthorized access attempts. The skill's behavior matches its described purpose of auditing UI code.
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from the author's official GitHub repository (
github.com/Prisma-Labs-Dev/frontend-skills). This is a functional requirement for retrieving the latest audit rules and targets a trusted vendor source. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted user-provided files. A malicious file could contain instructions intended to bias the audit report. However, the risk is minimal as the skill lacks high-risk capabilities like network exfiltration or code execution.
- Ingestion points: User-provided source files (SKILL.md)
- Boundary markers: Absent. The instructions do not specify the use of delimiters when reading external files.
- Capability inventory: None. The skill only outputs text findings and does not execute commands or access the network beyond fetching the guidelines.
- Sanitization: Absent. No filtering or escaping is applied to the content of the reviewed files.
Audit Metadata