gws-gmail
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 untrusted data from external emails which could contain malicious instructions for the agent.
- Ingestion points: Gmail messages, threads, and history resources in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in this file.
- Capability inventory: The skill allows sending emails (
+send), modifying settings, and managing labels, providing a range of actions an injected prompt could attempt to trigger. - Sanitization: No sanitization or filtering logic for processed email content is defined in the documentation.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands via the
gwsbinary to perform its tasks.
Audit Metadata