google-workspace

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user to paste the full OAuth redirect URL or authorization code and then instructs embedding that value verbatim into a command ($GSETUP --auth-code "THE_URL_OR_CODE..."), which requires the agent to handle and output a secret-like value directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI and docs (scripts/google_api.py and SKILL.md) explicitly fetch and return user emails, Drive files, Docs, and Sheets (e.g., gmail_get, docs_get, drive_search, sheets_get), meaning the agent ingests arbitrary third‑party/user‑generated content and may act on or use that content in its workflow.