The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill instructions or associated script.
[COMMAND_EXECUTION]: The script plan_rollout.py performs local file operations, reading from an input path and writing to an output path provided via command-line arguments.
[DATA_EXFILTRATION]: The skill does not utilize any network-capable tools or libraries; all processing is performed locally on the host.
[EXTERNAL_DOWNLOADS]: No external dependencies are fetched; the script relies exclusively on Python standard library modules (argparse, json, and typing).
[PROMPT_INJECTION]: The skill ingests user-provided data from a JSON file to generate documentation; while this represents a surface for indirect prompt injection if the output is later processed by an agent, the current implementation is a benign documentation generator.
[REMOTE_CODE_EXECUTION]: No patterns for remote code execution, dynamic code evaluation, or unsafe deserialization were detected.

feature-flag-rollout-planner