nestr-org
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill heavily utilizes the
nestrCLI to perform administrative actions, including managing workspaces, circles, roles, and user memberships. It includes the--yesflag which allows the agent to execute write operations without manual user confirmation. - [EXTERNAL_DOWNLOADS]: References external documentation and configuration resources hosted on the author's GitHub repository (
nestr-dev/nestr-cli). - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting and processing untrusted data from the Nestr platform.
- Ingestion points: Data is ingested from the platform via commands such as
nestr circles get,nestr roles get, andnestr users listas described inSKILL.md. - Boundary markers: There are no boundary markers or instructions to the agent to treat retrieved organizational data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses extensive write capabilities, including the ability to modify organization structure, change user roles, and manage app settings.
- Sanitization: No sanitization or validation of the data retrieved from the platform is performed before it is processed by the agent.
Audit Metadata