Deliver real-time stock quotes and market data with PubNub
94
65%
Does it follow best practices?
Impact
98%
1.81xAverage score across 15 eval scenarios
Risky
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Insecure credential handling detected (high risk: 1.00). The skill's output requirements explicitly ask to "Include PubNub SDK initialization with publish and subscribe keys," which encourages embedding API keys directly into generated code and thus could force the LLM to handle or emit secret values verbatim.