The Agent Skills Directory

[SAFE]: The skill is strictly focused on generating text for maintenance notifications. It does not include scripts, executables, or instructions that trigger high-risk operations.
[DATA_EXPOSURE]: The skill instructs the agent to read .agents/status-page-context.md to retrieve service names and communication guidelines. This file is a localized configuration document, and accessing it for content generation does not pose an exfiltration risk.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect injection as it processes user input and local file data. However, the risk is negligible because the skill does not have access to any tools (shell, network, or file writing) that could be exploited by malicious instructions embedded in the processed data.
Ingestion points: User prompts and the .agents/status-page-context.md file.
Boundary markers: None identified.
Capability inventory: No subprocesses, shell execution, or network capabilities are present in the skill.
Sanitization: No explicit sanitization of input data is performed before text generation.

maintenance