swiggy-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) tells the agent to run swiggy CLI searches (e.g., "swiggy food search-restaurants" against Swiggy servers) and parse returned restaurant/menu data—which are public, user-generated/untrusted third-party contents that the agent must interpret and which can influence its results and actions.