k2f-purchase-order
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a dependency using the command
npx skills add suzheng/k2f --skill k2f. This references a secondary skill module provided by the vendor 'suzheng'. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources which may contain untrusted content.
- Ingestion points: The agent is instructed to extract information from "requisitions, quotes, or line-item lists" provided by the user (SKILL.md).
- Boundary markers: The workflow does not specify the use of delimiters or clear instructions for the agent to ignore potentially malicious commands embedded within the input procurement documents.
- Capability inventory: The skill utilizes the
k2fengine to generate.K2Ffiles and export them to other file formats such as PDF (SKILL.md). - Sanitization: There are no documented procedures for sanitizing or escaping text extracted from external quotes or requisitions before it is interpolated into the purchase order blueprint.
Audit Metadata