ai-paragraph-rewriter
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides linguistic guidelines for humanizing text. It performs no system operations, network requests, or credential handling.\n- [NO_CODE]: No scripts or binaries are provided with this skill; it consists solely of Markdown instructions for the AI agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input for the purpose of rewriting.\n
- Ingestion points: User-provided text is ingested and displayed in the final response template in
SKILL.md.\n - Boundary markers: Minimal markers are used (e.g.,
**Original:**) to separate user input from agent instructions.\n - Capability inventory: The skill has no access to external tools, file systems, or network capabilities, making the impact of an injection attempt negligible.\n
- Sanitization: No sanitization is performed on user-provided text.
Audit Metadata