storybook-lesson
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to bypass safety guidelines or override behavior.
- [Indirect Prompt Injection] (SAFE): The skill ingests user input for lesson topics and tone settings. Evidence Chain: 1. Ingestion points: SKILL.md (User input). 2. Boundary markers: Absent. 3. Capability inventory: generate_image, tts. 4. Sanitization: Absent. The risk is categorized as SAFE because the tools are limited to media generation and do not allow system-level modification.
- [Data Exposure & Exfiltration] (SAFE): No access to sensitive file paths, credentials, or unauthorized network requests detected.
- [Unverifiable Dependencies] (SAFE): No external libraries, packages, or remote scripts are downloaded or executed.
Audit Metadata