nestr-agents
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of the
nestrCLI tool to perform operations such as listing agents, creating autonomous bots, and registering external connectors. - [EXTERNAL_DOWNLOADS]: The skill references setup documentation and configuration maps located on the vendor's official GitHub repository (
nestr-dev/nestr-cli). This is a legitimate vendor resource and is documented here for completeness. - [INDIRECT_PROMPT_INJECTION]: The skill constructs shell commands using input that may come from untrusted sources, creating a potential vector for command injection or argument manipulation. Ingestion points: User-provided variables such as
<agentId>,<nestId>,<connectorId>,<templateId>,--name,--description,--message, and--config. Boundary markers: The instructions do not include boundary markers or escaping logic for interpolating these variables into thenestrshell commands. Capability inventory: ThenestrCLI has capabilities to modify workspace state, assign roles, manage connector bindings, and trigger agent runs. Sanitization: There are no instructions for the agent to sanitize, validate, or escape the user input before executing the command.
Audit Metadata