google-ads-api-mcp-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to place user secrets into configuration files and command lines (JSON env blocks, shell exports, and a gcloud --set-env-vars command), which would require the LLM to include secret values verbatim in its output.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs installing and running remote code (pipx install google-ads-mcp and an optional pipx install git+https://github.com/googleads/google-ads-mcp.git), which will fetch and execute external package code at runtime (flagging the GitHub install URL as high-risk).

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly directs the agent/user to run system-level installation commands (including "sudo apt install pipx") and instructs the agent to "propose and execute" installs, which requires elevated privileges and can modify the host system state.