check-calendar-today
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the
osascriptutility to execute AppleScript commands on the host macOS system. This is the primary mechanism used to interface with the native Calendar application and fetch event data. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it processes data from calendar event titles and summaries which could contain instructions intended to subvert the agent's behavior.
- Ingestion points: Event summaries, titles, and times retrieved from the macOS Calendar via
SKILL.mdprocedure. - Boundary markers: Absent; there are no defined delimiters or instructions to ignore content within the fetched calendar data.
- Capability inventory: Local command execution via
osascriptto query system applications. - Sanitization: Absent; the skill does not perform validation or escaping of the text retrieved from calendar events before displaying it or passing it to the agent context.
Audit Metadata