top-banner-generator
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content for designing announcement banners and does not include any executable scripts, binary files, or network operations.
- [SAFE]: The instructions recommend reading local project context files (e.g., .claude/project-context.md) to align with project visual identity. This is standard behavior for context-aware agents and does not present a security risk as no network exfiltration tools are used.
- [SAFE]: An indirect prompt injection surface was evaluated. Ingestion points: .claude/project-context.md, .cursor/project-context.md. Boundary markers: Absent. Capability inventory: The skill is restricted to text generation only, with no access to file writing, system commands, or network requests. Sanitization: Not applicable for descriptive text output. The surface is determined to be safe due to the lack of exploitable tools.
Audit Metadata