pubnub/pubnub-multiplayer-gaming
Build real-time multiplayer games with PubNub game state sync
94
67%
Does it follow best practices?
Impact
97%
1.21xAverage 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.
W007: Insecure credential handling detected in skill instructions
What this means
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.
Why it was flagged
Insecure credential handling detected (high risk: 1.00). The prompt shows hard-coded publish/subscribe keys in the SDK initialization and requires including PubNub SDK initialization in outputs, which encourages embedding API keys directly (verbatim) into generated code or commands.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
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.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill's core workflow and code samples (SKILL.md and references/gaming-state-sync.md / gaming-setup.md) explicitly subscribe to and fetch messages from public PubNub channels (e.g., game-lobby, game.{roomId}.state, game.{roomId}.chat, matchmaking.* and history/hereNow/fetchMessages calls), meaning it ingests untrusted, user-generated third-party content and directly interprets those messages (state-delta, turn-start, chat, match-found, etc.) to drive game state and actions.
- Audited
- Security analysis