Build real-time auction platforms with PubNub bidding and countdowns
96
67%
Does it follow best practices?
Impact
100%
1.35xAverage 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: 1.00). The skill's code and workflow (SKILL.md and references like references/auction-bidding.md and auction-setup.md) subscribe to and fetch messages from PubNub channels (e.g., auction.<id>, catalog.active, user.<userId>.notifications) and process those user-generated, potentially untrusted messages (via pubnub.addListener, pubnub.fetchMessages, and PubNub Functions) to make decisions and trigger actions (bid acceptance, countdown updates, outbid notifications), which clearly exposes the agent to third-party content that could carry indirect prompt-injection-like instructions.