gws-gmail-read
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external email bodies and headers, which could contain instructions designed to override agent behavior.
- Ingestion points: The output of the
gws gmail +readcommand (SKILL.md). - Boundary markers: Absent. There are no explicit instructions or delimiters used to ensure the agent treats fetched content strictly as data.
- Capability inventory: The skill uses the
gwsbinary to interact with Google Workspace (SKILL.md). - Sanitization: No sanitization or safety-specific filtering of the retrieved email content is specified in the skill description.
- [COMMAND_EXECUTION]: The skill executes the
gwsCLI tool. This is expected functionality for a Google Workspace integration developed by this vendor.
Audit Metadata