tapsifood
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the
tapsifood-mcppackage from a public registry via theuvxcommand. This package is external to the skill and required for its tools to function. - [INDIRECT_PROMPT_INJECTION]: The skill tools ingest data from external Tapsi Food APIs, including user reviews and restaurant information, which could contain malicious instructions meant to influence the agent. 1. Ingestion points: External data is retrieved through tools such as
tf_reviews,tf_menu, andtf_search_dishes. 2. Boundary markers: The instructions do not specify any delimiters or safety warnings to help the agent distinguish between data and instructions. 3. Capability inventory: The skill tools are designed for read-only information retrieval. 4. Sanitization: There is no indication of content sanitization or validation for the data returned by the external APIs.
Audit Metadata