gogcli
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to read and parse user-generated content from Gmail (e.g., "gog gmail messages search ... --include-body"), Drive, Docs, Sheets, and Chat (e.g., "gog docs cat ", "gog drive download"), which can contain untrusted third‑party content from external senders that the agent would interpret and act on (reply, modify, create events), enabling indirect prompt injection risk.
Audit Metadata