google-docs

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that require embedding OAuth client_id/client_secret in config files and a CLI command that passes --client-secret (plaintext) as an argument, which encourages the LLM or user to emit secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and reads user-generated Google Docs/Drive content (see commands like "documents read", "documents get" and functions export_document_as_markdown / read_document_content that call the Google Docs and Drive APIs), so it ingests third‑party/untrusted document content that could carry indirect prompt injections.