k2f-fillable-pdf
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the command
npx skills add suzheng/k2f --skill k2f. This is a tool installation command used to set up the necessary K2F environment from the same author. - [EXTERNAL_DOWNLOADS]: The skill references an external dependency (
suzheng/k2f) to be downloaded and installed. As this resource is provided by the skill author ('suzheng'), it is considered a legitimate vendor resource for the skill's operation. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a design template that ingests user requirements, including legal and policy wording, to generate form blueprints.
- Ingestion points: User prompts containing form requirements, legal text, and submission paths in
SKILL.md. - Boundary markers: The instructions provide guidelines for separating static content (user text) from interactive field definitions.
- Capability inventory: The skill uses the
k2ftool to pack and export the final PDF document. - Sanitization: The instructions emphasize a 'verbatim gate', requiring the agent to use user-supplied legal and policy text without modification, which reduces the risk of the agent misinterpreting instructions embedded in that text as agent commands.
Audit Metadata