wattpad-publisher-formatter
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied manuscripts and chapter drafts, which are considered untrusted data.\n
- Ingestion points: The 'Manuscript / Chapter Drafts' input field in SKILL.md is the entry point for external data.\n
- Boundary markers: The instructions do not specify delimiters or 'ignore instructions' directives to isolate manuscript content.\n
- Capability inventory: The skill involves writing multiple files to the 'wattpad_build/' directory and executing a Python script.\n
- Sanitization: No validation or sanitization is mentioned to strip potential instructions from the manuscript text.\n- [COMMAND_EXECUTION]: The skill provides instructions for executing a local Python script for automation.\n
- Evidence: The SKILL.md documentation references running 'python helpers/python/format_wattpad_chapters.py' to process drafts.
Audit Metadata