api-designer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are strictly focused on API design principles. No override commands, jailbreak patterns, or attempts to extract system prompts were detected.
- [Data Exposure] (SAFE): No hardcoded credentials, API keys, or sensitive file paths (e.g., .ssh, .aws) are present. Examples use placeholder values and generic resource names.
- [Remote Code Execution] (SAFE): The skill does not perform any remote downloads, package installations, or piped shell execution. All code snippets provided in references are for illustrative purposes and are not executed by the skill.
- [Indirect Prompt Injection] (SAFE): While the skill is designed to process user-provided API specifications (ingestion point), it lacks any 'write' or 'execute' capabilities (e.g., file-write, network requests, or shell access), making it resilient to instructions embedded in processed data.
Audit Metadata