The Agent Skills Directory

[SAFE]: The skill provides templates and instructions for evaluating business outcomes. It lacks executable components, such as scripts or shell commands, posing no direct execution risk.- [SAFE]: File operations mentioned in the skill are limited to saving generated post-mortem records to a local directory and updating project context files. These actions are consistent with the skill's purpose and do not target sensitive system locations or credentials.- [SAFE]: The skill includes instructions to ingest external data such as performance metrics and customer signals. While this represents a data ingestion surface, the skill lacks the capabilities (e.g., network access or code execution) necessary to exploit this via indirect prompt injection.

post-mortem