AGENT LAB: SKILLS

gog-cli

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill issues commands that read and ingest user-generated, third-party content (e.g., gog gmail messages search --include-body, gog gmail thread get, gog drive download/get, gog chat messages list, gog docs/sheets read) from Google accounts and Drive/Chat/Classroom, so the agent would consume untrusted external content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:22 PM