latex-posters

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection within the schematic generation tool (scripts/generate_schematic_ai.py). User-provided diagram descriptions are interpolated directly into the prompt sent to the image generation model.
  • Ingestion points: Diagram descriptions provided via CLI arguments to the schematic generation scripts.
  • Boundary markers: None; the user input is directly embedded into the system prompt template.
  • Capability inventory: File system access for saving images and logs, network access for API calls, and subprocess execution for script coordination.
  • Sanitization: No input sanitization or delimiter-based separation is implemented for user-provided data.
  • [COMMAND_EXECUTION]: The scripts/generate_schematic.py script employs subprocess.run() to execute the secondary scripts/generate_schematic_ai.py script. This is a legitimate functional requirement for the skill's diagram generation workflow.
  • [EXTERNAL_DOWNLOADS]: The skill's AI-powered features rely on network communication with openrouter.ai to generate and review scientific visuals. OpenRouter is an established service for accessing large language and image models.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:24 AM