frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of text-based instructions for creative design guidance. No scripts, binaries, or system-level commands are included.\n- [SAFE]: There are no indicators of data exfiltration, credential theft, or unauthorized remote access. All design-related tasks are performed within the agent's standard conversational context.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to prioritize user-supplied design briefs over the skill's own stylistic defaults.\n
- Ingestion points: The agent ingests user-provided design briefs as defined in the SKILL.md instructions.\n
- Boundary markers: There are no specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the design brief.\n
- Capability inventory: The agent primarily generates HTML/CSS code and aesthetic plans based on these briefs.\n
- Sanitization: No content validation or sanitization of the input brief is implemented.
Audit Metadata