prompt-estruturado
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and designed to assist with prompt engineering. It does not perform any actions outside of the text conversation.
- [NO_CODE]: No scripts (Python, JavaScript, shell) or external binaries are included or referenced in the skill.
- [PROMPT_INJECTION]: The skill includes proactive safety instructions by requiring the agent to generate guardrails specifically designed to protect against prompt injection, jailbreaking, and unauthorized changes in task focus.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompt text to reformulate it. While this constitutes an ingestion point for untrusted data, the skill possesses no dangerous capabilities (network, file write, command execution) to exploit, and the final output is intended for the user's manual review.
Audit Metadata