soia-pkm-distill-article-opinion
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation describes installation via the
npx skills addcommand, which is a standard procedure for this platform's skill management system. - [DATA_EXPOSURE]: The skill accesses local files within the user's Obsidian vault (specifically under
<vault-articles-dir>/and_MOC/). This access is limited to the skill's stated purpose of reading article content and updating specific sections (## 我的看法). - [SAFE]: The skill includes explicit 'Core Principles' that prevent the AI from generating independent viewpoints, ensuring that all output is derived strictly from the user's verbal input. This reduces the risk of autonomous hallucinations or unintended content generation.
- [SAFE]: Instructions explicitly warn against storing sensitive information like API keys or sessions in the vault or repository, directing users to a private configuration directory instead.
Audit Metadata