deeper
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a set of logical steps for the AI to follow when rewriting a user's prompt. It does not include any scripts, external dependencies, or executable commands.
- [NO_CODE]: There are no code files or snippets provided with this skill; it is entirely composed of markdown instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and rewrite user prompts. While it does not utilize specific boundary markers or sanitization for the input data, it lacks any exploitable capabilities such as network requests, file writes, or shell command execution, rendering this attack surface benign.
Audit Metadata