The Agent Skills Directory

[SAFE]: The skill uses a local Python script (scripts/generate_postmortem.py) to process incident data. The script relies exclusively on Python's standard library and does not perform any network operations or access sensitive system files.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive environment variable accesses were detected in the instructions or scripts.
[REMOTE_CODE_EXECUTION]: There are no patterns of remote code execution, such as downloading and piping scripts to a shell or using dangerous functions like eval() or exec() on untrusted input.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied incident details (like titles and descriptions) and renders them into Markdown, the risk of indirect injection is minimal as the output is intended for human-readable documentation and does not trigger further automated actions with high privileges.

incident-retrospective