keep-it-simple
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): While the skill uses strong directive language and command-like headers (e.g., "Core Mandate", "Rules of Engagement"), these are used to define a persona rather than to bypass safety guardrails or override the underlying system prompt. The instructions are confined to the primary goal of the skill: encouraging simple code architecture.
- [Data Exposure & Exfiltration] (SAFE): There are no patterns indicating access to sensitive credentials, environment variables, or external network calls.
- [Remote Code Execution / Command Execution] (SAFE): The skill is composed entirely of text and markdown. It does not include scripts, dependencies, or commands that could be executed in a shell environment.
- [Indirect Prompt Injection] (SAFE): Although the skill is designed to process external plans and code implementations (potential injection surfaces), it lacks any exploitable capabilities such as file system writes or network access that could be triggered by malicious input.
Audit Metadata