The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's instructions and scripts are aligned with its stated purpose of incident documentation and analysis.- [DATA_EXPOSURE]: Section 6 contains Python templates that utilize the requests library to interact with a Marquez metadata server (defaulting to http://marquez:5000). This is a standard and legitimate method for retrieving lineage information to quantify the blast radius of data incidents.- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for processing incident data such as logs, stakeholder reports, and user feedback. While the instructions do not implement explicit boundary markers or sanitization for this external data, the risk is negligible as the skill's capabilities are focused on generating textual documentation for postmortem reports.

de-postmortem-writer