book-skill-generator
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes the local Python script
scripts/parse_book.pyusingpython3to transform OCR JSON data into structured Markdown files.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted OCR text and incorporates it into the instructions and descriptions of newly generated skills.\n - Ingestion points: Data is read from the user-provided file path (
<OCR_JSON_PATH>) inSKILL.md.\n - Boundary markers: The Python script identifies content using the
>prefix, which acts as a structural delimiter but does not provide security against embedded malicious instructions.\n - Capability inventory: The skill uses the
Writetool to install new skills in~/.claude/skills/, theReadtool to access local files, and theTasktool for parallel sub-agent processing.\n - Sanitization: Extracted text is directly interpolated into Markdown templates without semantic validation or instruction filtering.
Audit Metadata