google-postmaster-tools
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage from the official NPM registry. This is a vendor-provided tool required for the skill to interact with the Membrane platform. - [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the
membraneCLI for authentication, connection management, and executing specific actions like retrieving domain traffic statistics. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external data retrieved from Google Postmaster Tools.
- Ingestion points: Data returned from actions such as
list-traffic-statsorget-domaininSKILL.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potentially malicious content within the retrieved data.
- Capability inventory: The skill allows the execution of
membraneCLI commands, which can perform network operations and modify platform state. - Sanitization: There is no evidence of sanitization or validation performed on the data fetched from Google's APIs before it is incorporated into the agent's context.
Audit Metadata