The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute a local Python script (scripts/generate_schematic.py) for creating scientific schematics. The provided command template (python scripts/generate_schematic.py "your diagram description") directly interpolates a string into the shell command.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its intended purpose of analyzing external scientific papers and utilizing parts of that content in shell commands.
Ingestion points: The skill is designed to read and process research papers, scientific claims, and study methodologies (as specified in the skill's description and core capabilities).
Boundary markers: There are no boundary markers or instructions provided to the agent to sanitize the input or ignore embedded instructions within the diagram descriptions.
Capability inventory: The skill's allowed tools include Read, Write, Edit, and Bash.
Sanitization: No sanitization or validation of the input strings is mentioned or implemented before the data is passed to the Bash tool.
[NO_CODE]: Although SKILL.md provides instructions and a command template for running scripts/generate_schematic.py, this script file is not included in the provided 7-file skill bundle.

scientific-critical-thinking