gmail-access
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the CLI to list/search/read Gmail messages (see "Gmail Commands" and "Rule 1
- Replies" where the CLI auto-detects sender by reading original email headers), meaning it ingests arbitrary third-party/user-generated email content from Gmail which can materially influence drafting and sender-selection behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's setup guide requires running a remote installer with "curl https://mise.run | sh", which fetches and executes remote code at setup time and mise is a required runtime dependency for the skill.
Audit Metadata