k2f-menu
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 processes untrusted user data (venue notes, dish lists, and brand cues) to generate menu content, creating a surface for indirect prompt injection. \n
- Ingestion points: User-provided venue notes and dish lists as described in the Workflow section of SKILL.md. \n
- Boundary markers: None specified in the instructions to delimit or isolate user-supplied content. \n
- Capability inventory: The skill utilizes the 'k2f' tool for operations like unpacking, packing, and exporting files (SKILL.md). \n
- Sanitization: No instructions are provided for escaping or sanitizing external content before interpolation. \n- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a core dependency using 'npx skills add suzheng/k2f', which involves fetching code from a remote source. This resource is authored by the same vendor. \n- [COMMAND_EXECUTION]: The workflow requires the execution of shell commands for skill installation and workspace management, including 'npx skills add', 'unpack', 'init', 'pack', and 'export'.
Audit Metadata