superset-automate

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the superset CLI to list projects and workspaces, and to create, run, and modify automations. These are functional requirements for the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided descriptions of tasks to draft automation prompts. To mitigate risks associated with processing untrusted input, the instructions explicitly require the agent to display the exact command and prompt to the user for confirmation before any automation is created.
  • [SAFE]: No obfuscation, malicious persistence, unauthorized exfiltration, or safety bypass patterns were detected. The use of temporary files (/tmp/automation-prompt.md) for multiline prompts is a standard practice and does not involve sensitive system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 03:10 PM