book-layout-designer
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data in the form of manuscript structures or sample chapters, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The 'Agent Contract' in
SKILL.mdspecifies that the agent accepts manuscript structures or sample chapters as input.\n - Boundary markers: There are no specific boundary markers or instructions to treat ingested data as non-executable text to prevent the agent from following instructions embedded within the manuscript.\n
- Capability inventory: Across the provided files, there are no subprocess calls, file-system write operations, network requests, or executable scripts; the skill's output is limited to layout specifications.\n
- Sanitization: The 'Process' section includes an instruction to check for sensitive metadata or private data in sample content, providing a basic manual validation step.\n- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration files, with no associated scripts or executable code provided.
Audit Metadata