The Agent Skills Directory

[SAFE] (SAFE): The provided Python scripts (architecture_diagram_generator.py, project_architect.py, dependency_analyzer.py) contain only boilerplate logic for input validation and reporting. No dangerous system calls or network operations are present.
[Indirect Prompt Injection] (LOW): All three scripts in the scripts/ directory ingest data from a user-provided target file system path. This represents a potential entry point for untrusted data into the agent's context.
Ingestion points: target command-line argument in architecture_diagram_generator.py, project_architect.py, and dependency_analyzer.py.
Boundary markers: Not implemented; scripts currently only perform path validation and simple reporting.
Capability inventory: The scripts possess local file system access permissions (reading/validating paths).
Sanitization: Standard pathlib validation ensures the target path exists but no content sanitization is performed.

senior-architect