novel-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses a local Python command (python3 scripts/create_epub.py) to generate ebooks from markdown chapters. This is a legitimate functional requirement of the skill's primary purpose.
  • [NO_CODE] (SAFE): The analyzed files consist of Markdown instructions and reference templates. No executable scripts were provided, limiting the direct security risk of the current file set.
  • [INDIRECT PROMPT INJECTION] (SAFE): The skill ingests user input via the AskUserQuestion tool to drive story developments. Although this represents an ingestion surface for untrusted data, it is a core feature of the interactive novel workflow and does not facilitate privilege escalation or exfiltration. Evidence: 1. Ingestion: User responses from Phase 1 and 2; 2. Boundaries: Absent; 3. Capability: File writing and local script execution; 4. Sanitization: Absent.
  • [DATA_EXPOSURE & EXFILTRATION] (SAFE): No hardcoded credentials, sensitive system paths, or unauthorized network requests were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM