gws-gmail-reply
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates replying to emails using external content, which presents a surface for indirect prompt injection attacks.\n- Ingestion points: The
--bodyflag inSKILL.mdserves as the primary ingestion point for potentially untrusted data from existing emails.\n- Boundary markers: No explicit delimiters or safety instructions are defined to separate untrusted content from agent instructions.\n- Capability inventory: The skill allows execution of thegwsCLI to send emails, representing a significant capability that could be abused if an injection occurs.\n- Sanitization: No input validation or sanitization is performed on the data passed to the CLI command.
Audit Metadata