Build real-time applications with PubNub pub/sub messaging
85
65%
Does it follow best practices?
Impact
88%
1.27xAverage 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 core workflow and examples (SKILL.md and references/publish-subscribe.md and references/sdk-patterns.md) instruct the agent to subscribe to PubNub channels and add message listeners that process incoming messages—i.e., ingesting untrusted/user-generated messages from public channels that could contain instructions affecting behavior.