simplex-cli-admin

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill revolves around the use of the simplex-cli tool for backend management tasks. It includes extensive command templates for user management, credit adjustments, and system statistics, as well as instructions for building the tool locally.
  • [PROMPT_INJECTION]: Evaluated for indirect prompt injection potential due to data ingestion.
  • Ingestion points: CLI output processing (references/cli-cheatsheet.md).
  • Boundary markers: Instructions mandate explicit user confirmation and restating command impact before execution (SKILL.md).
  • Capability inventory: Subprocess execution of simplex-cli for mutating database and email operations (references/business-logic.md).
  • Sanitization: Not explicitly implemented for CLI output, though risk is mitigated by required user confirmation steps.
  • [SAFE]: The skill includes proactive security guidance, such as warning against pasting tokens and passwords into public logs and recommending non-interactive, secure login methods using standard input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:59 PM