book-distiller
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities detected. The skill performs standard local file parsing using legitimate libraries and contains no network exfiltration or remote code execution vectors.
- [PROMPT_INJECTION]: The skill processes untrusted external content (books), which introduces a theoretical surface for indirect prompt injection.
- Ingestion points: Data enters the system via the document reading functions in
scripts/parse_book.py. - Boundary markers: Absent. The prompts in
references/PROMPT_TEMPLATES.mddo not utilize delimiters (e.g., XML tags) or specific instructions to ignore embedded commands within the book text. - Capability inventory: The skill includes file system read and write capabilities within the
scripts/parse_book.pyscript. - Sanitization: Absent. No filtering or escaping is applied to the extracted text before it is passed to the AI agent for distillation.
Audit Metadata