a6-plugin-ai-proxy
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve the use of the a6 CLI tool for creating and updating gateway routes (e.g., a6 route create) and synchronizing configuration (a6 config sync).\n- [DATA_EXFILTRATION]: The skill facilitates network requests to well-known and trusted AI service providers, including OpenAI, Anthropic, DeepSeek, and Google Vertex AI, for legitimate proxying functionality.\n- [SAFE]: The skill does not contain any malicious code, prompt injections, or obfuscated content. It correctly employs placeholders for all sensitive API keys and authentication tokens, ensuring that credentials are not exposed in the instructions.
Audit Metadata