playground

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes a literal authentication token and shows code/commands that embed that token verbatim for WebSocket auth, so the agent would need to output or reproduce a secret value directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's connect script and docs (scripts/connect.js, SKILL.md, README.md) explicitly connect to the public WebSocket wss://playground-bots.fly.dev/bot and ingest/display room descriptions and peer messages/events (e.g., 'message', 'room'), which are untrusted, user-generated third-party content that the agent reads and can act on.