gemini-history-analyzer
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes extracting and then reading Google Takeout ZIP contents (e.g., “*.txt conversation transcripts” and surrounding context) into the agent for analysis, which is outsider-authored free text from the user’s Takeout export rather than text authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata