The Agent Skills Directory

[SAFE]: The skill is a well-structured set of Python scripts and documentation for technology evaluation. A thorough inspection of the code, including the logic for TCO calculation and migration assessment, confirms that the skill operates entirely within the local environment. It does not perform network requests, exfiltrate data, or attempt to access sensitive system files like credentials or SSH keys.
[COMMAND_EXECUTION]: The skill defines several Python scripts intended to be executed by the agent to process data. These scripts (stack_comparator.py, tco_calculator.py, ecosystem_analyzer.py, security_assessor.py, and migration_analyzer.py) use standard Python libraries to perform logic and arithmetic. No instances of eval(), exec(), or unsafe sub-process calls were found.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from various formats including natural language, JSON, and YAML via format_detector.py. While this establishes an ingestion point for untrusted data, the skill's capabilities are restricted to generating reports and matrices. There are no high-risk tools available to the skill (such as network access or privilege escalation) that would allow an injection to facilitate a compromise.

tech-stack-evaluator