agentstack-server-debugging
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands via the mise task runner for starting development clusters and running project-specific services like agentstack-server and agentstack-cli.
- [PROMPT_INJECTION]: The skill accepts user-provided input to be passed as arguments to the agentstack-cli tool, which represents a surface for indirect prompt injection.
- Ingestion points: User-defined arguments in CLI commands.
- Boundary markers: None.
- Capability inventory: Local command execution via mise.
- Sanitization: No sanitization is performed on the command arguments.
Audit Metadata