The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where untrusted user input is included in instructions for the AI model. * Ingestion points: The prompt variable in scripts/generate_schematic_ai.py sourced from user input. * Boundary markers: Absent; the user text is directly interpolated into the system-level guidelines. * Capability inventory: The skill uses subprocess.run to execute local Python scripts and requests for network communication. * Sanitization: None; user input is not escaped or validated before use in LLM prompts.
[COMMAND_EXECUTION]: The scripts/generate_schematic.py script executes a local Python utility using subprocess.run. This implementation is secure as it uses a list for arguments and does not invoke a shell.
[EXTERNAL_DOWNLOADS]: The skill performs API calls to openrouter.ai to facilitate scientific diagram generation and quality review. OpenRouter is a well-known service and is handled as a safe external dependency.

pptx-posters