frontend-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies external repository documentation as a source of instruction, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read AGENTS.md, README files, and component documentation within the codebase (SKILL.md).
- Boundary markers: No specific delimiters or warnings to ignore instructions within ingested files are provided.
- Capability inventory: The agent's environment generally includes filesystem access, shell execution, and network access for web development.
- Sanitization: The instructions do not prescribe sanitization or validation of the content within the documentation files before processing.
Audit Metadata