book-translation-guide
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection through processed book content. 1. Ingestion points: Markdown source files and ZIP packages (SKILL.md). 2. Boundary markers: Absent; sub-agent prompts lack delimiters or instructions to ignore embedded commands. 3. Capability inventory: File system access via shell commands (sed, grep, cat, rm) and sub-agent task invocation. 4. Sanitization: Absent; content is passed directly to agents or shell utilities without filtering.
- [COMMAND_EXECUTION]: The skill defines a workflow using standard Unix utilities (sed, grep, tail, mkdir) to split, process, and verify book chapters.
- [SAFE]: External links point to the author's own GitHub repository (madeyexz), representing legitimate vendor resources. No hardcoded credentials or obfuscation techniques were identified.
Audit Metadata