playdotfun

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The workflow explicitly requires capturing and saving the user's creator API key (user UUID) and inserting it verbatim into generated artifacts (e.g., a tag and code snippets), which forces the agent to handle and output secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill requires fetching and inspecting public, user-published Play.fun content (e.g., the Claim Ownership step that checks a game's public HTML meta tag and the MCP public tools like list_games / get_game_leaderboard and use of a public gameUrl in the register_game flow), so the agent will read untrusted third‑party pages/entries as part of its required workflow and those results can change subsequent actions.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill includes explicit, purpose-built crypto/token operations: it supports "add token rewards" / "launch a Playcoin" and documents an MCP tool named launch_playcoin which requires Privy wallet authentication (wallet auth/signing). This is a specific blockchain/crypto action (launching a token and involving wallet auth), not a generic browser or API caller, so it grants direct financial execution capability.