recipe-reschedule-meeting
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external Google Calendar events, which may contain untrusted content.
- Ingestion points: The
gws calendar +agendaandgws calendar events getcommands inSKILL.mdbring external event data into the agent's context. - Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious content within event titles or descriptions.
- Capability inventory: The skill uses
gws calendar events patchinSKILL.mdto modify calendar data based on the retrieved information. - Sanitization: There is no evidence of sanitization or validation of the event data before it is used to construct the patch request.
- [COMMAND_EXECUTION]: The skill requires the execution of the
gws(Google Workspace) command-line tool to perform agenda lookups and event modifications.
Audit Metadata