The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell commands for its core functionality, including figure generation, document conversion, and PDF export.
Evidence: The skill uses Bash to execute scripts/generate_schematic.py, google-chrome --headless, and libreoffice --headless commands.
[COMMAND_EXECUTION]: The skill creates an attack surface for command injection by interpolating untrusted user data into shell command arguments.
Ingestion points: The agent is instructed to use the user's research topic and content as parameters for figure-generation scripts.
Boundary markers: No explicit delimiters or warnings are used to isolate user data from the command structure.
Capability inventory: The skill is granted Bash, Read, Write, and Edit permissions, allowing it to execute arbitrary shell commands.
Sanitization: The instructions lack guidance on sanitizing or escaping user-provided text before it is inserted into command-line strings (e.g., python scripts/generate_schematic.py "... [TOPIC] ...").
[EXTERNAL_DOWNLOADS]: The skill references external dependencies and software tools required for the workflow, though it does not perform automated downloads.
Evidence: Documentation identifies python-pptx, google-chrome, and libreoffice as necessary components for the poster creation and export process.

pptx-posters