li-distribute
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it reads and processes the full content of video scripts found in local directories. If these scripts contain malicious instructions, they could potentially influence the agent's actions or the output of the 'li-writer' tool.
- Ingestion points: Local files searched via Glob in '01-内容生产/待发布的内容/中短视频/' and '02-已发布内容/短视频/'.
- Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore embedded instructions within the scripts.
- Capability inventory: The skill utilizes glob searching, file reading, and file writing capabilities.
- Sanitization: There is no evidence of sanitization or content validation before the data is passed to the 'li-writer' generation tool.
Audit Metadata