minimax-cli-runtime
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: References the installation of the
mini-agenttool from its official repository on GitHub. - [COMMAND_EXECUTION]: Invokes the
mini-agentCLI to perform automated tasks, utilizing command-line arguments for prompt transfer. - [PROMPT_INJECTION]: Accesses and parses external agent logs located in
~/.mini-agent/log/which contain content from remote LLM responses. This creates an indirect prompt injection surface. - Ingestion points: Reads log files from
~/.mini-agent/log/(SKILL.md). - Boundary markers: Utilizes specific block headers and separators (REQUEST/RESPONSE/TOOL_RESULT) to parse structured data.
- Capability inventory: Executes
mini-agentCLI and Node.js scripts. - Sanitization: Implements regex-based redaction (
redactSecrets) to prevent API keys from appearing in diagnostic outputs.
Audit Metadata