mcp-app-builder
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Extensive review of the skill instructions and reference materials revealed no malicious patterns, prompt injections, or unauthorized code execution attempts.
- [EXTERNAL_DOWNLOADS]: The skill contains multiple links to technical documentation on the
developers.openai.comdomain. These are well-known and trusted resources consistent with the skill's purpose of aiding app development. - [DATA_EXFILTRATION]: There are no network operations or sensitive file access patterns. The provided guidance explicitly emphasizes security best practices, such as avoiding the leakage of secrets and internal identifiers in application payloads.
- [PROMPT_INJECTION]: The instructions establish a professional development workflow. There are no attempts to override agent safety constraints or extract system prompts.
- [COMMAND_EXECUTION]: The skill does not contain shell commands, scripts, or instructions for the agent to execute arbitrary local code.
Audit Metadata