The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/generate_schematic.py to invoke a secondary Python script (generate_schematic_ai.py). The command is constructed using a list of arguments rather than a single string with a shell, which follows security best practices to prevent command injection.
[EXTERNAL_DOWNLOADS]: The scripts/generate_schematic_ai.py script makes network requests to openrouter.ai using the requests library to generate and evaluate scientific schematics. This is a legitimate functional requirement for the skill's AI features and utilizes a well-known LLM aggregation service.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text prompts to generate scientific diagrams. These prompts are interpolated into larger system instructions sent to an external AI model. While this presents an indirect prompt injection surface, the risk is low given the specific application (image generation) and the use of system-level guidelines to bound the model's behavior.

pptx-posters