hwpx-templates
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runto execute a local utility script,scripts/fix_namespaces.py, which is included within the skill package. This script is used for post-processing HWPX files to ensure compatibility with Hangul Office by normalizing XML namespaces and removing specific elements using regular expressions. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-uploaded HWPX templates (
input/custom-template.hwpx). - Ingestion points: The skill uses
ObjectFinderto extract and print text content from user-uploaded HWPX files to identify placeholders. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the templates are provided in the workflow.
- Capability inventory: The skill possesses file read/write capabilities, ZIP archive manipulation, and the ability to execute the provided local Python script via subprocess.
- Sanitization: There is no evidence of sanitization or filtering applied to the text extracted from the user-uploaded templates before the agent processes it to design replacement mappings.
Audit Metadata