Deliver real-time sports scores, play-by-play, and scoreboards with PubNub
96
65%
Does it follow best practices?
Impact
100%
2.94xAverage score across 15 eval scenarios
Risky
Do not use without reviewing
Security
2 findings — 1 high severity, 1 medium severity. 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 explicitly requires including PubNub publish and subscribe keys in SDK initialization and shows key placeholders, which would lead an agent to request, accept, or embed real secret keys verbatim in generated code/commands, creating an exfiltration risk.
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 workflow and reference docs explicitly subscribe to and fetch messages from PubNub channels (e.g., wildcard subscriptions like "sports.<league>.games.*" in references/sport-updates-setup.md and message history via pubnub.fetchMessages in references/*), including fan engagement channels (e.g., sports.fan.reactions.*, polls) which are user-generated and are parsed/acted on (updateScoreboard, publishWithPush, publishEvent), so untrusted third-party content is ingested and can directly influence actions and decisions.