k2f-exam-paper
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, untrusted data to generate exam content.
- Ingestion points: The workflow involves reading syllabus topics, rubrics, past papers, and source readings (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to ignore embedded instructions within these documents.
- Capability inventory: The skill involves file creation (content_and_design.md), package creation (.K2F packages), and using a compilation engine to export files (PDFs).
- Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a supporting component from the same author.
- Evidence: The instruction
npx skills add suzheng/k2f --skill k2fin SKILL.md downloads and installs a prerequisite skill necessary for the workflow.
Audit Metadata