recipe-draft-email-from-doc

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly reads content from a Google Doc via "gws docs documents get" and copies that user-generated/untrusted document text to use as the Gmail message body, so third-party doc content directly influences an agent action (sending email).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 10:51 PM