kordoc-parse-pages
Warn
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npm execto download and run thekordocpackage from the NPM registry at runtime. Whilepdfjs-distis a well-known library,kordocis a third-party package without a verified version or provenance in the skill instructions. - [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands (via
npm exec) that interpolate user-supplied data, specifically the document path and page range. This creates a surface for shell command injection if a user provides a malicious file path containing shell metacharacters. - [REMOTE_CODE_EXECUTION]: The use of
npm exec --package=kordocconstitutes the execution of remote code fetched dynamically from an external repository (NPM). - [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse and ingest content from external documents (HWP, HWPX, PDF), creating an attack surface for indirect prompt injection where instructions hidden in those documents could influence the agent's behavior.
- Ingestion points: Local document files specified by the user and processed in
SKILL.mdunder the Commands section. - Boundary markers: Absent; the instructions do not specify any delimiters or safety headers for the parsed content.
- Capability inventory: Access to shell execution through
npm execas defined inSKILL.md. - Sanitization: Absent; no mention of sanitizing or escaping the parsed document content before returning it to the agent context.
Audit Metadata