The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (architecture_diagram_generator.py, project_architect.py, and dependency_analyzer.py) to perform its core functions. These operations are intended for local project analysis and are consistent with the skill's primary purpose.
[EXTERNAL_DOWNLOADS]: The skill documentation references standard package managers such as npm and pip for installing dependencies from well-known public registries. No suspicious remote code execution or untrusted script downloads (e.g., curl|bash) were found.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to analyze external, untrusted project source code and configuration files.
Ingestion points: Target project paths and source code directories provided by the user for analysis.
Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions found within analyzed project data.
Capability inventory: File system access and local script execution used for auditing dependencies and generating system diagrams.
Sanitization: No explicit validation, escaping, or filtering of the content within the analyzed files is documented.

senior-architect