harden
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing templates and guidelines for frontend resilience. It does not include any scripts, command execution, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external design context and user-defined risky scenarios during the preparation phase.
- Ingestion points: Data is ingested via the target argument and referenced design contexts ($frontend-design).
- Boundary markers: The skill does not define specific delimiters for ingested data.
- Capability inventory: The skill possesses no capabilities for file writing, network exfiltration, or subprocess execution.
- Sanitization: No explicit sanitization of input data is performed, but the lack of executable capabilities renders this surface non-exploitable.
Audit Metadata