web-design-guidelines-apply
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a set of design guidelines and does not contain any executable code, command execution, or network operations. Analysis of the workflow and reference map found no malicious patterns.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read local project files to align UI implementation with project standards. This represents a potential surface for indirect prompt injection from files within the working directory.\n
- Ingestion points: Files matching
docs/**/design-system.md,DESIGN_SYSTEM.md,docs/**/style-guide.md,theme.ts, andtheme/index.tsare read by the agent (defined inSKILL.md).\n - Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore embedded prompts within these files.\n
- Capability inventory: None. The skill does not request or utilize dangerous capabilities like file writing, network access, or command execution.\n
- Sanitization: Absent. There is no explicit sanitization for the content of the referenced files.
Audit Metadata