multi-account-operator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the vendor's official command-line interface (
postbridge-cli) for all automated tasks. This usage is explicitly restricted within the skill's metadata and represents standard tool interaction for the post-bridge-hq vendor. - [SAFE]: External links and documentation references are pointed towards the vendor's official infrastructure, including the API documentation at
api.post-bridge.comand the project repository on GitHub. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied content, such as captions and media files, for distribution to external social platforms. While this constitutes an attack surface for indirect prompt injection, it is a necessary component of the skill's primary function and does not show signs of exploitation.
- [COMMAND_EXECUTION]: The provided CLI examples for account management and posting are legitimate administrative commands for the Post Bridge platform and do not attempt to execute unauthorized system commands or escalate privileges.
Audit Metadata