family-menu
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script,
scripts/generate_menu.py, to generate the weekly menu in PDF format. This script uses standard document generation libraries and does not perform any suspicious system operations.\n- [EXTERNAL_DOWNLOADS]: The skill performs web searches to gather information on seasonal ingredients, recipes, and local restaurants. These network operations are limited to research and are appropriate for the skill's stated purpose.\n- [PROMPT_INJECTION]: The skill processes untrusted data from web search results (such as recipes and restaurant reviews), which presents a potential surface for indirect prompt injection. However, the risk is minimal as the skill's capabilities are restricted to document generation and lacks access to sensitive user data or system configurations.\n - Ingestion points: External information is retrieved via web searches for seasonal produce, high-protein recipes, and restaurant recommendations (specified in
SKILL.md).\n - Boundary markers: None; there are no specific instructions or delimiters to isolate or ignore instructions that might be embedded in the retrieved web content.\n
- Capability inventory: The skill has the ability to generate and save PDF files using
scripts/generate_menu.pyand access the internet via web search tools.\n - Sanitization: None; the instructions do not include steps to sanitize or validate the content retrieved from external websites before processing it.
Audit Metadata