li-writer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and local content libraries (such as '内容素材库/读书笔记库/INDEX.md') to generate text. This creates a vulnerability where instructions embedded in the input data could potentially influence the agent's logic.
- Ingestion points: User inputs for script topics and local material library files (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters for the processed content.
- Capability inventory: The skill utilizes filesystem write capabilities to save content and invokes internal agent routing.
- Sanitization: No specific input validation or filtering is required by the instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to create and write Markdown files to the '01-内容生产/待发布的内容/中短视频/' directory (SKILL.md). This interaction with the local filesystem is a core functional requirement of the skill.
Audit Metadata