gws-workflow-weekly-digest
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, specifically Google Calendar and Gmail, which can contain attacker-controlled content.
- Ingestion points: Calendar agenda and Gmail triage summaries are accessed by the skill.
- Capability inventory: The skill uses the
gwsCLI for read-only operations. - Boundary markers: There are no explicit delimiters or instructions to the AI agent to ignore or isolate instructions that might be embedded in meeting titles or email content.
- Sanitization: The skill does not perform any visible sanitization or validation of the retrieved content.
- [COMMAND_EXECUTION]: The skill relies on the execution of a local command-line interface tool to fetch data.
- Evidence: Requires the
gwsbinary and executesgws workflow +weekly-digestas shown in the metadata and usage section.
Audit Metadata