data-analyst
Warn
Audited by Snyk on May 12, 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 explicitly instructs the agent to ingest third-party data sources (e.g., "Spreadsheets: Google Sheets URL / local path" and "APIs: REST endpoints, GraphQL" in SKILL.md, plus the analyze_template.py and scripts that load CSV/Excel and database connections) so it will read and act on untrusted/user-provided content that can influence analysis and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata