init-docs
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell-like commands such as
mkdir -p docsto initialize the project directory structure. This is a standard operation for a documentation tool. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when using the
--scanmode. - Ingestion points: Reads local Java controller files using the glob pattern
ruoyi-modules/ruoyi-*/src/main/java/**/controller/*Controller.javato extract information for documentation. - Boundary markers: None present to distinguish between legitimate code and potentially malicious instructions hidden in code comments.
- Capability inventory: Directory creation (
mkdir), file reading, and file writing (Markdown generation). - Sanitization: No explicit sanitization or filtering of the content read from source files before it is used to generate documentation.
Audit Metadata