recipe-card
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted text input, such as recipes copied from external websites, cookbooks, or messages.
- Ingestion points: The skill accepts recipe data "in any form" as user-provided input.
- Boundary markers: The instructions do not explicitly mandate the use of delimiters or specific warnings to ignore instructions embedded within the source recipe text.
- Capability inventory: The skill includes the capability to interact with note-taking applications (e.g., the author's Scratchpad connector) to save the formatted results.
- Sanitization: The instructions focus on preserving original recipe cues and quantities and do not describe a method for sanitizing the input data.
Audit Metadata