book-bible

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted user-provided story content to perform consistency checks. 1. Ingestion points: Reads 'new content' provided by the author. 2. Boundary markers: None. 3. Capability inventory: Uses file:read and file:write permissions for local workspace files as defined in SKILL.md. 4. Sanitization: None. This surface is inherent to the skill's primary purpose and is considered safe as there are no high-risk capabilities like network access or shell execution.
  • [NO_CODE]: The skill consists entirely of natural language instructions and configuration metadata, containing no executable scripts, binaries, or remote code patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:41 PM
Security Audit — agent-trust-hub — book-bible