gws-workflow-standup-report
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that are not fully controlled by the agent platform.
- Ingestion points: Processes meeting titles, event descriptions, and task lists from Google Workspace via the
gwsCLI. - Boundary markers: No delimiters or isolation instructions are present to prevent the agent from following instructions potentially embedded in calendar events or tasks.
- Capability inventory: The skill utilizes the
gwsbinary to fetch data from the user's Google account. - Sanitization: No explicit sanitization or filtering of the retrieved data is documented.
- [COMMAND_EXECUTION]: The skill executes local system commands to retrieve data.
- Evidence: The skill requires the
gwsbinary as a prerequisite and executes commands such asgws workflow +standup-report.
Audit Metadata