gmail-access

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to retrieve an API access token via a command and include it verbatim in an Authorization header using curl (-H "Authorization: Bearer $tok"), which exposes the secret value in generated commands.

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow for this skill monitors and reads emails via a Gmail CLI, allowing an outsider to submit arbitrary free text into the monitored inbox.