The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local Python scripts for specialized tasks like diagram generation and PDF processing.
Evidence: SKILL.md contains instructions to run scripts/generate_schematic.py and skills/scientific-slides/scripts/pdf_to_images.py.
Analysis: The implementation in scripts/generate_schematic.py uses subprocess.run with an argument list rather than a shell string, preventing shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The schematic generation feature performs network operations to interact with an external AI service.
Evidence: scripts/generate_schematic_ai.py uses the requests library to connect to https://openrouter.ai/api/v1/chat/completions.
Analysis: OpenRouter is a well-known service for AI models. This network activity is required for the skill's stated functionality and does not involve downloading untrusted executable content.
[CREDENTIALS_UNSAFE]: The skill includes logic for handling API authentication for its schematic generation features.
Evidence: scripts/generate_schematic_ai.py searches for the OPENROUTER_API_KEY in environment variables and .env files.
Analysis: No hardcoded secrets were found. The skill follows standard security best practices by requiring credentials to be managed via the environment.

peer-review