superimage-generator

Pass

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: LOWPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface. Ingestion Point: 'input_prompt' field in JSON examples (e.g., bw-window-portrait.json). Boundary Markers: Absent. Capability Inventory: Limited to text generation/display for external image models. Sanitization: Absent. The risk is low as the skill does not trigger high-privilege side effects or execute arbitrary code.
  • [EXTERNAL_DOWNLOADS] (INFO): Documentation references external API endpoints (e.g., Black Forest Labs API). No suspicious remote code downloads or piped executions (curl|bash) were found.
  • [SAFE] (SAFE): No malicious obfuscation, persistence mechanisms, or credential exposures were detected across the 19 analyzed documentation and configuration files.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 14, 2026, 02:53 PM