The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_schematic.py executes a secondary AI generation script using subprocess.run. The implementation uses a list of arguments and the local Python interpreter, which avoids shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to the openrouter.ai API to access diagram generation and quality review models. This is an expected use of a well-known service for the skill's primary functionality and does not involve downloading executable code.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided descriptions and interpolates them into model prompts without sanitization or boundary markers, creating a surface for prompt injection. 1. Ingestion points: The prompt command-line argument in scripts/generate_schematic.py and the user_prompt parameter in scripts/generate_schematic_ai.py. 2. Boundary markers: None used in the prompt templates. 3. Capability inventory: The skill uses the Write tool to save image files and JSON logs to the local filesystem. 4. Sanitization: No validation or filtering is performed on the user input before it is sent to the LLM context.

scientific-schematics