book-architect

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill package is composed entirely of static markdown files and templates for book structuring. No executable scripts, binaries, or source code files are included.
  • [SAFE]: No network operations, sensitive file access, or hardcoded credentials were found in any of the files.
  • [SAFE]: The skill does not attempt to install or use any third-party packages or remote scripts.
  • [PROMPT_INJECTION]: While the skill ingests external data (book concepts and research reports), creating a surface for indirect prompt injection, it lacks high-privilege tool access (such as shell execution or network calls), which makes the risk negligible as the only impact would be on the generated text output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 05:53 PM
Security Audit — agent-trust-hub — book-architect