The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (process_analyzer.py, handoff_analyzer.py, improvement_scorer.py) to process process-mapping data. These scripts use standard Python libraries and do not perform any dangerous operations, network calls, or privilege escalation.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided JSON files containing process metadata. While this represents an ingestion point for external data, the processing is limited to mathematical analysis and metric generation within local scripts, posing no significant risk of prompt injection.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file path access, or network exfiltration patterns were detected in the scripts or instructions.

process-mapper