rewrite
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided text for rewriting and polishing. This creates an attack surface where hidden instructions in the input text could potentially influence the AI's behavior or output. Evidence in SKILL.md: The skill is explicitly triggered by user input intended for processing, such as '润色', '改稿', or '这篇读起来太像 AI 了'.
Audit Metadata