The Agent Skills Directory

[SAFE]: No security issues detected. The skill defines standard tools for interacting with the Google Calendar API without any malicious modifications or overrides.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external content from calendar events:
Ingestion points: Event titles and descriptions are processed via list_events and get_event (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the guidelines.
Capability inventory: The skill allows creating, updating, and deleting events via tools like create_event and update_event (SKILL.md).
Sanitization: No sanitization or validation of event content is specified.
[DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file access (e.g., .ssh or .aws), or unauthorized network activity was found. The skill operates exclusively through specified tool interfaces.

google-calendar