The Agent Skills Directory

[COMMAND_EXECUTION]: The orchestrator script scripts/orchestrate_edge_pipeline.py coordinates the pipeline by executing local Python scripts using subprocess.run.
Evidence: The script programmatically locates and executes stages such as auto_detect, hints, and concepts within the project structure using sys.executable and argument lists.
Security: All command execution is performed without a shell (shell=False), which effectively prevents command injection vulnerabilities from user-supplied file paths or arguments.
[SAFE]: The skill implements secure data handling by using yaml.safe_load to parse YAML files and json.loads for JSON files, mitigating the risk of arbitrary code execution during deserialization.
[SAFE]: Analysis of the instructions and scripts reveals no network exfiltration patterns, hardcoded credentials, persistence mechanisms, or attempts to bypass agent safety guidelines.

edge-pipeline-orchestrator