The Agent Skills Directory

[PROMPT_INJECTION]: Potential surface for indirect prompt injection through automated project file analysis.
Ingestion points: The skill utilizes scripts/project_architect.py and scripts/dependency_analyzer.py to analyze target project directories.
Boundary markers: Absent. No specific instructions are provided to the agent to distinguish between project data and system instructions.
Capability inventory: The skill is designed to execute Python scripts, manage packages via npm and pip, and interact with deployment tools like Docker and kubectl.
Sanitization: Absent. The skill documentation does not mention validation or sanitization of content read from the target project files.
[COMMAND_EXECUTION]: The skill uses several internal Python scripts for its core functionality, including architecture_diagram_generator.py, project_architect.py, and dependency_analyzer.py.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install dependencies using npm and pip from a requirements.txt file and provides an installation command to fetch the skill's markdown definition from a remote GitHub repository.

senior-architect