book-tutor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of natural language instructions and configuration metadata without any accompanying scripts or executables.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local files, which serves as an ingestion point for potentially untrusted data. 1. Ingestion points: Reads project configuration from CLAUDE.md, chapter content from source files, and session history from a tracker file. 2. Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate external content from the agent's core instructions. 3. Capability inventory: The agent can read local files and write summaries or notes to local directory paths specified in the configuration. 4. Sanitization: There is no explicit sanitization or validation of the chapter content before it is processed by the agent.
Audit Metadata