google-ads-connect

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for sensitive credentials (developer token, client ID/secret, refresh token) and to save them into a JSON file, which requires the agent to accept and potentially echo those secret values verbatim (exfiltration risk).

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

• Direct money access detected (high risk: 1.00). The skill explicitly includes an "Execution (Optional)" section with a mutation script that performs actions like pausing keywords, adding negative keywords, and adjusting bids (python skills/google-ads-connect/scripts/mutate.py ... --pause-keywords ... --add-negatives ... --bid-adjust ...). Those are explicit API/mutation actions that change ad settings and directly affect ad spend/budgets, so this is Direct Financial Execution capability.