rhwp-edit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves its primary instructions and file lists by executing
npx -y @nomadamas/k-skill@0, which downloads content from the vendor's package repository. - [REMOTE_CODE_EXECUTION]: The process of fetching instructions and executing document operations involves running remote code locally via npx using vendor-managed packages.
- [COMMAND_EXECUTION]: The skill performs document modifications (such as inserting text, creating tables, and replacing strings) by invoking CLI subcommands including
insert-text,replace-all, andset-cell-text. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill processes user-provided HWP/HWPX document files through commands like
info,search, andlist-paragraphsto identify structure and content. - Boundary markers: Absent. The instructions do not specify the use of delimiters or guardrails to prevent the agent from potentially following instructions embedded within the document data.
- Capability inventory: The skill has the ability to execute CLI commands and perform filesystem write operations.
- Sanitization: Includes logic to prevent document corruption (e.g., UTF-16 length validation) but lacks specific filtering for natural language instructions embedded within the processed document content.
Audit Metadata