The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_schematic.py uses subprocess.run to execute the internal generate_schematic_ai.py script. The implementation is secure as it uses a list for command arguments, which prevents shell injection attacks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to describe scientific diagrams and interpolates this content into prompts for external AI models.
Ingestion points: User prompts for diagram generation are processed in scripts/generate_schematic_ai.py.
Boundary markers: The skill does not use explicit delimiters or instructions to ignore potential commands within the user input.
Capability inventory: The skill has the capability to perform network requests to OpenRouter and write image and log files to the filesystem.
Sanitization: No specific sanitization or filtering is applied to user-supplied text before prompt interpolation.
[DATA_EXPOSURE]: The skill handles an API key (OPENROUTER_API_KEY) for external services. Security is maintained by using a whitelist of allowed environment variables when spawning sub-processes, ensuring that unrelated sensitive environment data is not leaked to child processes.

latex-posters