03-danh-gia-hieu-suat
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the use of Model Context Protocol (MCP) servers to pull advertising data. It references official services from Meta (mcp.facebook.com) and Google, as well as third-party marketing technology providers like Pipeboard and Adspirer. These references are part of the skill's core functionality for data-driven auditing.
- [SAFE]: The skill adheres to best practices for marketing audits. It focuses on analytical frameworks (5 Whys, Decision Trees, Quality Gates) and diagnostic logic. No instances of prompt injection, obfuscation, or unauthorized access were found.
- [COMMAND_EXECUTION]: While the skill mentions MCP tools, these are platform-level integrations intended for secure data retrieval in a controlled environment. The skill itself does not invoke dangerous shell commands or scripts.
Audit Metadata