google-drive

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill template explicitly shows and instructs placing OAuth client_id/client_secret in plaintext (a YAML file) and passing a client secret as a command-line argument (--client-secret), which would cause the agent to handle or emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accesses Google Drive (see SKILL.md and scripts/google-drive.py) and supports listing, fullText searching (references/drive-queries.md), getting and downloading files from users' Drive—which are untrusted/user-generated contents the agent will read/ingest at runtime and that could influence subsequent actions.