The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a LegacyCodeAnalyzer class in references/system-assessment.md that utilizes subprocess.run to execute system git commands. Specifically, it runs git log to identify "hotspots" by tracking file change frequency.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill performs extensive local file system operations to facilitate codebase analysis. In references/system-assessment.md, the LegacyCodeAnalyzer recursively scans the project directory for Python files and reads their content to identify code smells and dependencies. Additionally, it includes functionality to write technical debt reports and GraphViz dependency diagrams directly to the disk.
[EXTERNAL_DOWNLOADS]: The documentation suggests the installation and use of several third-party Python libraries for testing and analysis, such as mutmut, coverage.py, hypothesis, syrupy, and approvaltests. These are well-known development tools within the Python ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is designed to ingest and process untrusted external codebase data.
Ingestion points: The code in references/system-assessment.md reads raw Python source code from the file system for analysis.
Boundary markers: None identified; the skill processes file content directly through AST parsing and regular expressions.
Capability inventory: The skill has the ability to execute shell commands (git), write to the file system (pathlib), and perform network requests (httpx).
Sanitization: No specific sanitization or filtering of the ingested source code is performed before analysis.

legacy-modernizer