frontend-design
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a context-gathering protocol that reads from a local file named
.impeccable.md. This represents an indirect prompt injection surface where untrusted data within the project file could be used to influence the agent's code generation output. - Ingestion points:
.impeccable.md(root directory) - Boundary markers: Absent; the agent is instructed to read the file and proceed immediately if context is found.
- Capability inventory: The skill is used to generate functional, production-grade frontend code (HTML, CSS, JavaScript).
- Sanitization: No specific validation, filtering, or escaping of the context data is performed before it is used to guide generation.
Audit Metadata