gws-gmail-watch
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the
gwsbinary to perform Gmail monitoring. This tool is a vendor-provided CLI for interacting with Google Workspace services. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a data ingestion pipeline from an untrusted external source (Gmail). If the agent processes the resulting NDJSON stream or files, it may encounter malicious instructions embedded in email content.
- Ingestion points: Reads email bodies and metadata via the
gws gmail +watchcommand (SKILL.md). - Boundary markers: The provided documentation does not specify the use of delimiters or 'ignore' instructions for the ingested data.
- Capability inventory: The skill can write email content to the local file system using the
--output-dirflag and accesses private communication data. - Sanitization: No specific sanitization or filtering of the external email data is documented within this skill.
Audit Metadata