Build real-time order tracking and delivery driver systems with PubNub
91
65%
Does it follow best practices?
Impact
94%
1.84xAverage score across 15 eval scenarios
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 0.80). The skill's code and workflow explicitly subscribe to and load history from PubNub channels (e.g., driver.*.location, order.*.status, chat.order.* and dispatch.order-claims) and use PubNub Functions to read and act on those user-generated messages (e.g., resolving claims, recalculating ETA, republishing sanitized locations or issuing driver commands), meaning untrusted third-party content is ingested at runtime and can materially influence actions.