The Agent Skills Directory

[SAFE]: The skill follows security best practices for a cloud auditing utility. The provided Python script cloud_posture_check.py performs static analysis of JSON configuration files without executing remote code or accessing unauthorized system resources. Its behavior matches the stated purpose of cloud security posture management.- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes external JSON files provided by the user. However, the risk is minimal as the script performs deterministic logic on structured data and does not interpolate the content into natural language prompts for further autonomous agent actions.
Ingestion points: scripts/cloud_posture_check.py reads JSON files via file path arguments.
Boundary markers: The script expects structured JSON data and performs specific value checks rather than general text processing.
Capability inventory: The script's capabilities are limited to reading local files and writing report output.
Sanitization: Employs the standard json library for parsing, preventing common injection vectors associated with unstructured data.

cloud-security