book2skill
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a well-defined and professional methodology (RIA-TV++) for knowledge management and distillation. It provides a robust framework for structural, interpretive, and critical analysis of source material.
- [EXTERNAL_DOWNLOADS]: The skill is designed to process user-provided external documents (PDF, EPUB, or TXT formats) to perform its distillation task. While this involves ingesting untrusted content, the methodology requires the agent to interpret, verify, and rewrite the findings in its own words, which serves as a mitigation against indirect prompt injection.
- [COMMAND_EXECUTION]: The core skill definition in SKILL.md utilizes agent orchestration capabilities to spawn specialized sub-agents (e.g., framework-extractor, principle-extractor) for parallel data processing. This is a standard and legitimate use of agent tools for complex task automation.
- [PROMPT_INJECTION]: The instructions and methodology documents do not contain any patterns intended to bypass safety filters or override system constraints. Instead, they provide strict quality redlines and execution flows to ensure the integrity of the generated skill packs.
Audit Metadata