google-maps

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill embeds API-key-like literals in examples (export FETCHER_API_KEY="bby_live_xxxxxxxxxxxx" and an MCP header "Authorization": "Bearer bby_live_..."), which encourages or requires exposing secrets verbatim in configs/requests and thus risks secret exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). In the Google Maps API skill, the required runtime workflow performs HTTP GET calls to outsider-provided search/query and then returns matching place details/reviews from that query, which means user-controlled free text (“query”) can drive retrieval/ingestion of free-form review text at runtime via /api/place/search → /api/place/{fid}/reviews (and /api/review/{id}).

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

• Direct money access detected (high risk: 1.00). The skill explicitly includes paid operations and payment mechanics: it exposes a topup_credits operation and documents an x402 pay-per-call flow that requires USDC on specific blockchains (Base, Polygon, Arbitrum, Monad, Solana) and notes that @x402/fetch "signs and retries automatically." Those are specific crypto payment/signing capabilities (sending transactions/top-ups), which constitute direct financial execution ability.