k2f-idml
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as marketing briefs and draft copy, to create publication skeletons. \n
- Ingestion points: External briefs and draft copy mentioned in Step 1. \n
- Boundary markers: There are no instructions to wrap or delimit user content with specific warnings to the agent to ignore embedded commands. \n
- Capability inventory: The skill utilizes the k2f tool for file packing and exporting, and requires shell command execution for initial setup. \n
- Sanitization: No evidence of input sanitization or filtering was found. \n- [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing a core component from the vendor's repository using the 'npx skills add suzheng/k2f' command. \n- [COMMAND_EXECUTION]: The setup workflow involves executing a shell command to initialize the required skill environment.
Audit Metadata