skills/simonwong/skills/write-article/Gen Agent Trust Hub

write-article

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions focus entirely on article writing and editorial workflows. It emphasizes distinguishing between user claims and AI suggestions, and requires user confirmation for key points, which is a good security practice for preventing accidental instruction following from processed materials.
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to the 'Chinese Copywriting Guidelines' hosted on GitHub (sparanoid/chinese-copywriting-guidelines). This is a well-known community standard for Chinese typography and formatting and is referenced neutrally for educational purposes.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided materials and external documents, it implements several safeguards. It instructs the agent to verify facts against sources, identify missing data, and seek user confirmation before finalizing stances, reducing the risk of being influenced by embedded instructions in the source materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 11:51 AM