gws-gmail-watch
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external email content, creating an attack surface for indirect prompt injection if the agent subsequently interprets these emails as instructions.\n
- Ingestion points: Incoming email content monitored through the
gws gmail +watchcommand.\n - Boundary markers: No delimiters or warnings are provided to the agent to differentiate email data from system instructions.\n
- Capability inventory: The skill uses the
gwsCLI tool and can write to the local filesystem via the--output-dirflag.\n - Sanitization: No sanitization or validation of email content is performed by the skill itself.\n- [COMMAND_EXECUTION]: The skill relies on the execution of the
gwsbinary to monitor accounts and manage Google Cloud Pub/Sub resources.
Audit Metadata