pp-squarespace

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs embedding API tokens/cookies into commands or env vars (e.g., squarespace-pp-cli auth set-token YOUR_TOKEN_HERE, export COMMERCE_AUTHORIZATION=... and account cookie usage), which requires the agent/LLM to include secret values verbatim in generated output.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is executing the squarespace-pp-cli binary (via Direct Use / Agent Mode) which calls Squarespace APIs and ingests their JSON responses into the agent context; those responses are outsider-authored content from a third-party service (Squarespace) rather than user-authored text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisites instruct running remote installers that fetch and execute code at runtime—e.g. "npx -y @mvanhorn/printing-press-library install squarespace --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/commerce/squarespace/cmd/squarespace-pp-cli@latest"—and the CLI obtained from those sources is a required dependency.