skills/ckokoski/authorclaw/book-bible/Gen Agent Trust Hub

book-bible

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and permissions are consistent with the stated purpose of world-building and consistency management.
  • [PROMPT_INJECTION]: The skill processes user-provided book content for consistency checks, representing a surface for indirect prompt injection. Evidence Chain: (1) Ingestion points: User-provided story content. (2) Boundary markers: Absent. (3) Capability inventory: file:read and file:write within workspace/memory/book-bible/. (4) Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:42 AM
Security Audit — agent-trust-hub — book-bible