a6-plugin-ai-prompt-decorator

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for configuring the ai-prompt-decorator plugin within the Apache APISIX ecosystem. It contains no malicious code or instructions.\n- [CREDENTIALS_UNSAFE]: The skill uses industry-standard placeholders such as sk-your-key and sk-key in examples. These are not real credentials and are used according to best practices for documentation.\n- [COMMAND_EXECUTION]: The shell commands provided (a6 route create, curl) are legitimate instructions for using the specified tools to configure and test the plugin functionality.\n- [INDIRECT_PROMPT_INJECTION]: While the plugin being documented processes external messages, the skill itself describes using system-level decorators to increase security by enforcing safety guidelines and internal instructions at the proxy level.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 12:22 PM
Security Audit — agent-trust-hub — a6-plugin-ai-prompt-decorator