The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs subprocess.run within scripts/generate_slide_image.py to invoke its internal AI generation script and within scripts/validate_presentation.py to check LaTeX compilation via pdflatex. These calls are performed using list-based arguments, which is a safe implementation that prevents command injection.
[EXTERNAL_DOWNLOADS]: The scripts/generate_slide_image_ai.py script makes outbound HTTP requests to the openrouter.ai API. This is a well-known service utilized by the skill to generate slide visuals and perform automated quality reviews using LLMs. This behavior is consistent with the skill's stated purpose.
[CREDENTIALS_UNSAFE]: The skill follows secure practices for credential management by requiring users to provide an API key through environment variables or a .env file, rather than using hardcoded secrets within the codebase.
[SAFE]: The skill includes comprehensive documentation and templates that promote best practices for scientific communication. It does not exhibit any signs of prompt injection, data exfiltration, or obfuscation.

scientific-slides