book-distill

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local initialization script (book_distill_init.sh) to bootstrap the working directory. This script performs routine file system tasks such as directory creation and metadata duplication.
  • [PROMPT_INJECTION]: The skill processes untrusted external book content as its primary input. While this represents a surface for indirect prompt injection, the risk is mitigated by the skill's lack of network access and the confined nature of its file system operations within the plugin's workspace.
  • [EXTERNAL_DOWNLOADS]: The documentation references external GitHub repositories for methodology and design inspiration, but the skill does not perform any remote code downloads or executions at runtime.
  • [DATA_EXFILTRATION]: The skill references local configuration paths for the Kobo platform (kobodl.json) in a helper script, but it does not read or transmit sensitive user credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:06 PM
Security Audit — agent-trust-hub — book-distill