superset-10x

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides a command to install the Superset CLI: curl -fsSL https://superset.sh/cli/install.sh | sh. This pattern involves fetching a shell script from the vendor's official domain and piping it directly to the system shell for execution. While this is a common installation method for CLI tools, users should verify the script source before execution.- [COMMAND_EXECUTION]: The agent is instructed to execute several superset CLI commands to audit the user's current environment, including identity checks (auth whoami) and listing resources like workspaces, agents, and hosts.- [EXTERNAL_DOWNLOADS]: The skill references an external resource for CLI installation hosted at https://superset.sh/cli/install.sh.- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection as it ingests and processes data from external CLI command outputs and user-provided descriptions of their workflow.
  • Ingestion points: Outputs from superset * list commands and user workflow topics provided as arguments.
  • Boundary markers: The skill includes explicit instructions that the audit phase must remain read-only.
  • Capability inventory: The skill has the capability to execute shell commands, create agents, manage workspaces, and configure hosts.
  • Sanitization: Security is maintained through mandatory user confirmation ("Set it up now") before the agent performs any state-changing operations or creates new resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 08:38 AM
Security Audit — agent-trust-hub — superset-10x