good-writing-zh
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown and text documentation (SKILL.md, docs/guide-en.md, references/guide.md, docs/source.txt). No scripts, binaries, or automated command execution patterns were found.
- [SAFE]: No network operations, external downloads from untrusted sources, or data exfiltration behaviors were detected.
- [PROMPT_INJECTION]: The skill accepts user-provided articles for rewriting, which is an ingestion point for indirect prompt injection. 1. Ingestion points: User-provided text or file paths (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are specified for the input data. 3. Capability inventory: No dangerous tools are utilized; the skill does not use subprocesses, network tools, or file-writing tools. 4. Sanitization: No input validation or escaping is performed. While a surface exists, it is categorized as safe because the skill lacks the capabilities required to perform harmful actions beyond altering the immediate text output.
Audit Metadata