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.pyscript employssubprocess.run()to execute the secondaryscripts/generate_schematic_ai.pyscript. 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.aito generate and review scientific visuals. OpenRouter is an established service for accessing large language and image models.
Audit Metadata