gongmunseo
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script using the
Bashtool to perform HWPX generation. It references a hardcoded absolute path in the developer's home directory:/Users/chris_gomdori/workspace/kordoc/dist/cli.js. This exposes local system information (usernames) and may lead to execution failures or unexpected behavior in different environments. - [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied topics and content as input to generate administrative documents, which are then processed by the
kordoctool. - Ingestion points: User-provided strings via the
[작성할 내용/주제]argument inSKILL.md. - Boundary markers: None identified. The content is interpolated directly into Markdown templates.
- Capability inventory: The skill uses the
Bashtool to run commands andWrite/Edittools to handle files. - Sanitization: There are no explicit instructions to escape or sanitize the user input before it is written to a Markdown file and passed as a shell argument to the
nodecommand, which could potentially be exploited if the HWPX generator does not handle malformed Markdown safely.
Audit Metadata