gws-gmail-read
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gwscommand-line utility to retrieve email data. This is a functional requirement for the skill's purpose as an email reader tool.- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data from Gmail messages, which constitutes an indirect prompt injection surface. - Ingestion points: Email bodies and headers are retrieved via the
gws gmail +readcommand inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are present in this skill to distinguish email content from agent instructions.
- Capability inventory: The skill allows the agent to read and display private email data.
- Sanitization: The skill does not implement explicit sanitization or validation of the retrieved message content before it is processed by the agent.
Audit Metadata