read-podcast-script-generator
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for conversational style transformation. Its operations are limited to reading provided text or local markdown files and generating stylized responses based on internal reference materials.
- [DATA_EXPOSURE]: The skill contains a hardcoded reference to a local directory path (
/Users/ugreen/Documents/obsidian/每日播客/). This reveals a specific local file system structure, likely belonging to the intended user, but it does not represent an exfiltration risk as no network tools or external data transmission patterns are present. - [PROMPT_INJECTION]: As the skill ingests user-provided text and external files, it is theoretically subject to indirect prompt injection. However, the risk is negligible because the skill lacks dangerous capabilities such as shell execution, file writing, or network access that could be abused by malicious content in the source material.
Audit Metadata