banner-design
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on design methodologies, aspect ratios, and platform-specific constraints. Analysis found no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution. The skill operates purely within the context of generating design advice and creative assets.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests user-provided data such as brand context and technical specifications.
- Ingestion points: User-supplied specifications, copy, and brand assets are referenced in
SKILL.mdas primary inputs. - Boundary markers: No explicit delimiters are used to separate user-provided content from the skill's internal instructions.
- Capability inventory: No executable scripts, network requests, or system-level commands are present in the skill's instructions or referenced files.
- Sanitization: The instructions do not specify any validation or sanitization methods for the external inputs.
Audit Metadata