just-do-it
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill uses language such as "overrides verbose planning behavior" and "Immediately execute the user's request." These instructions are designed to bypass the agent's internal Chain-of-Thought reasoning, which is a mechanism often used to evaluate the safety and appropriateness of a request.
- Indirect Prompt Injection (LOW): By discouraging the agent from asking clarification questions and demanding "action over explanation," the skill makes the agent more susceptible to malicious commands hidden in user-provided data. 1. Ingestion points: User requests for code, commands, or documents. 2. Boundary markers: Absent. 3. Capability inventory: Commands, code generation, and configuration output. 4. Sanitization: Absent.
Audit Metadata