blog-writing-zh
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs text-to-text transformation and writing assistance. Thorough inspection of all 24 files shows no signs of prompt injection, data exfiltration, obfuscation, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as Obsidian notes and foreign articles. This is a functional requirement for its primary purpose. The skill includes instructions to maintain factual accuracy and offers specific strategies for material conversion that reduce the impact of potential injection within processed data.
- [EXTERNAL_DOWNLOADS]: The documentation provides installation instructions via npx referencing the author's own repository (github.com/leoluyi/skills). This is a standard and transparent distribution method for this vendor.
Audit Metadata