The Agent Skills Directory

[SAFE]: The skill uses Python's ast module and regular expressions to perform static analysis. This process does not execute the source code being analyzed, ensuring a safe evaluation environment.
[EXTERNAL_DOWNLOADS]: The requirements.txt file includes requests and python-dotenv. These are well-known, industry-standard packages. Currently, they are not called within the logic of pattern_detector.py, complexity_analyzer.py, or other scripts.
[PROMPT_INJECTION]: The skill processes external data via the code_input parameter, which presents a surface for indirect prompt injection.
Ingestion points: The code_input parameter receives untrusted source code for analysis.
Boundary markers: The instructions do not define explicit markers to isolate the analyzed code from the agent's context.
Capability inventory: The skill's scripts are limited to analytical logic and do not possess capabilities for file writing, system command execution, or network communication.
Sanitization: The skill validates Python syntax using ast.parse, but does not filter the semantic content of the input code for potential injection attempts.

code-refactoring-advisor