gws-calendar-insert
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the
gwscommand-line utility to perform write operations to Google Calendar. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user data and interpolates it into shell commands without explicit safety boundaries.
- Ingestion points: The flags
--summary,--location,--description, and--attendeeinSKILL.mdaccept arbitrary text from users or external data sources. - Boundary markers: The skill lacks explicit delimiters or instructions telling the agent to treat the flag values as data rather than instructions.
- Capability inventory: The skill has the capability to execute the
gwsbinary with arguments provided by the user. - Sanitization: There are no instructions for sanitization, escaping, or validation of the input strings before they are passed to the CLI tool.
Audit Metadata