frontend-designer
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection due to its core functionality of processing external, untrusted content.\n
- Ingestion points: In SKILL.md (Phase 1 and 2), the agent is instructed to collect design assets such as mockups, PDFs, and brand guidelines from external URLs.\n
- Boundary markers: The prompt lacks instructions to delineate external content or to ignore potential instructions embedded within those external files.\n
- Capability inventory: The skill utilizes Write, MultiEdit, and Bash tools (mentioned in the SKILL.md Analysis Guidelines), which could be leveraged if a malicious instruction is successfully injected via the ingested design data.\n
- Sanitization: No sanitization or validation logic is defined to check the safety of external design assets or URLs before the agent processes them.
Audit Metadata